Quantum entanglement can be employed in some distributed communication tasks to reduce computation and communication overheads, yielding speedups over their classical counterparts. However, existing quantum Byzantine protocols often entail excessive communication and entanglement resource consumption. Conversely, classical schemes face insecurity with the impending reality of quantum computers. To address these challenges, we present a novel quantum Detectable Weak Byzantine Agreement (DWBA) protocol with high practicability, security and optimal fault-tolerance bound. For all n players, our protocol can complete the consensus of infinite classical information via fixed n + 1 -entangled qubits and a digest function, which requires infinite entanglement resources in previous schemes. Moreover, our protocol can tolerate arbitrary t ( t < n ) faulty players without necessitating any additional initial setup information (e.g., digital signature, private random coins). In terms of efficiency, our protocol only requires O (1) rounds and O ( ( n − t ) 2 ) communication complexity, constituting an order of magnitude improvement over previous protocols. In addition, the DWBA problem solved by our protocol is inherently stronger than the 3-player Detectable Byzantine Agreement (DBA) problem solved by previous protocols, and in a weaker but sufficiently practical model, our protocol can achieve Weak Byzantine Agreement (WBA).

Enhancing defense through model ensemble is an emerging trend, where the challenge lies in how to use ensemble knowledge to counter Out-of-Distribution (OOD) attacks. In this paper, we propose the Reliable Defense Ensemble (REE) to address this issue. REE optimizes the ensemble knowledge of models through aggregation and enhances multidimensional robust performance through collaboration. It employs the Dynamic Synergy Amplification for weight allocation and strategy adjustment. Furthermore, we design a new Kernel Anomaly Smoothing Detection Module, which detects anomalous attacks using a smoothing feature function based on Gaussian kernel mean embedding and a multi-layer feedback structure. Particularly, we build a framework that uses reinforcement learning to iteratively fine-tune the parameters of inter-model communication and consensus. Extensive experimental results show that REE outperforms current state-of-the-art methods by a large margin in defending against OOD attacks.

In the context of Continual Semantic Segmentation (CSS), replay-based methods tend to achieve better performance than knowledge distillation-based ones, as the former utilizes additional data to transfer old knowledge. However, this advantage is at the cost of necessitating additional space for storing the generative model and extra time for continual training. To address this predicament, we propose a novel CSS framework, namely Adversarial Attack-based Knowledge Retention (AAKR). The AKKR framework generates specific adversarial samples by adding images, and uses them to retain old knowledge. Specifically, we leverage adversarial attacks to generate adversarial images for incremental samples. By imposing additional constraints within these attacks, we enhance the transfer of old knowledge, thereby reinforcing the understanding of previously learned information. Furthermore, we design an attack probability module that adjusts adversarial attack directions based on training feedback. This module effectively encourages the new model to learn old knowledge from poorly protected classes, significantly improving knowledge transfer effectiveness. Our comprehensive experiments demonstrate the efficacy of AAKR, and showcase that AAKR surpasses state-of-the-art competitors on benchmark datasets.

Adversarial attack and defense have been extensively explored in classification tasks, but their study in semantic segmentation remains limited. Moreover, current attacks fail to act as strong underlying attacks for adversarial training (AT), making it difficult to achieve segmentation robustness against strong attacks. In this paper, we present RP-PGD, a novel Region-and-Prototype based Projected Gradient Descent attack tailored to fool segmentation models. In particular, we propose a region-based attack, which leverages a spatial-temporal way to separate the pixels into three disjoint regions, and highlights the attack on the crucial True Region and Boundary Region. Moreover, we introduce a prototype-based attack to disrupt the feature space, further enhancing the attack capability. To boost the robustness of segmentation models, we inject adversaries generated by RP-PGD into the clean data and perform AT. Extensive experiments on multiple datasets showcase that RP-PGD generates adversaries with faster convergence and stronger attack effectiveness, surpassing state-of-the-art attacks by a large margin. Consequently, RP-PGD serves as a strong underlying attack for segmentation models to perform AT, assisting them in defending against a variety of strong attacks without incurring additional computational costs during inference.

In the field of multimodal learning, controlling the training of unimodal encoders from different perspectives is a primary approach to addressing Training Imbalance. However, the inherent capacity limitations of the modality affect the model’s capability. Therefore, generating adversarial examples that can achieve balanced transferability remains a challenging and perplexing problem. In this paper, we propose the InterModality Balanced Attack (MOBA) to address this problem. MOBA leverages Aggregated Modality Perturbation (AMP), which exploits the unbalanced effects of text and image perturbations to maximize the impact on the victim model. AMP capitalizes on the intrinsic feature connections between modalities during the optimization process, adjusting perturbations through Cross-Modality Discrepancy Loss to enhance attack success rates. Additionally, we devise the Transferability-Enhanced Evolution (TEE) to overcome the issue of diminished attack transferability due to model capacity limitations. TEE employs Transfer-Driven Optimization Loss to alleviate overfitting in single models, thereby enhancing the generalization ability.

3D reconstruction and simulation, although interrelated, have distinct objectives: reconstruction requires a flexible 3D representation that can adapt to diverse scenes, while simulation needs a structured representation to model motion principles effectively. This paper introduces the Mesh-adsorbed Gaussian Splatting (MaGS) method to address this challenge. MaGS constrains 3D Gaussians to roam near the mesh, creating a mutually adsorbed mesh-Gaussian 3D representation. Such representation harnesses both the rendering flexibility of 3D Gaussians and the structured property of meshes. To achieve this, we introduce RMD-Net, a network that learns motion priors from video data to refine mesh deformations, alongside RGD-Net, which models the relative displacement between the mesh and Gaussians to enhance rendering fidelity under mesh constraints. To generalize to novel, user-defined deformations beyond input video without reliance on temporal data, we propose MPE-Net, which leverages inherent mesh information to bootstrap RMD-Net and RGD-Net. Due to the universality of meshes, MaGS is compatible with various deformation priors such as ARAP, SMPL, and soft physics simulation. Extensive experiments on the D-NeRF, DG-Mesh, and PeopleSnapshot datasets demonstrate that MaGS achieves state-of-the-art performance in both reconstruction and simulation.

Out-of-distribution (OOD) fine-tuning has emerged as a promising approach for anomaly segmentation. Current OOD fine-tuning strategies typically employ global-level objectives, aiming to guide segmentation models to accurately predict a large number of anomaly pixels. However, these strategies often perform poorly on small anomalies. To address this issue, we propose an instance-level OOD fine-tuning framework, dubbed LNOIB (Leaving No OOD Instance Behind). We start by theoretically analyzing why global-level objectives fail to segment small anomalies. Building on this analysis, we introduce a simple yet effective instance-level objective. Moreover, we propose a feature separation objective to explicitly constrain the representations of anomalies, which are prone to be smoothed by their in-distribution (ID) surroundings. LNOIB integrates these objectives to enhance the segmentation of small anomalies and serves as a paradigm adaptable to existing OOD fine-tuning strategies, without introducing additional inference cost. Experimental results show that integrating LNOIB into various OOD fine-tuning strategies yields significant improvements, particularly in component-level results, highlighting its strength in comprehensive anomaly segmentation.

In the developing field of visual object tracking, the robustness and resilience of detection modules against adversarial perturbations is critical. Traditional attacks have shown limitations in maintaining long-term deception, which is mainly reflected in that they are often only effective for a short period of time, or only have an impact on a specific single frame of images, rather than continuously and effectively mislead objects in continuous video sequences. Therefore, the tracker tends to quickly recover to the correct tracking state in the face of continuously changing adversarial attacks, showing robustness against occasional detection anomalies. In order to solve these problems, we propose Multi-Strategy Adversarial Attack (MSAA). MSAA imposes specific constraints on the decision-making ability of the model, regulating the priority of modification to candidate bounding boxes, including offset and size. In addition, the strategy to construct a predefined hijacking trajectory includes a direction-aware perturbation and a center matching scheme to hijack the feature-aware module to a predefined target. To the best of our knowledge, this is the first time that a unified perspective is adopted to address the problem from diffuse deviation to target hijacking. Our method not only enhances the persistence and concealment of attacks, but also achieves more precise control in multi-target scenarios, which has not been fully addressed in traditional adversarial attack methods. Experiments show that MSAA greatly outperforms state-of-the-art attack methods on multiple public datasets.

Numerical vector aggregation plays a crucial role in privacy-sensitive applications, such as distributed gradient estimation in federated learning and statistical analysis of key-value data. In the context of local differential privacy, this study provides a tight minimax error bound of$O(\frac{ds}{n\epsilon ^{2}})$, where$d$represents the dimension of the numerical vector and$s$denotes the number of non-zero entries. By converting the conditional/unconditional numerical mean estimation problem into a frequency estimation problem, we develop an optimal and efficient mechanism called Collision. In contrast, existing methods exhibit sub-optimal error rates of$O(\frac{d^{2}}{n\epsilon ^{2}})$or$O(\frac{ds^{2}}{n\epsilon ^{2}})$. Specifically, for unconditional mean estimation, we leverage the negative correlation between two frequencies in each dimension and propose the CoCo mechanism, which further reduces estimation errors for mean values compared to Collision. Moreover, to surpass the error barrier in local privacy, we examine privacy amplification in the shuffle model for the proposed mechanisms and derive precisely tight amplification bounds. Our experiments validate and compare our mechanisms with existing approaches, demonstrating significant error reductions for frequency estimation and mean estimation on numerical vectors.

Recently, many sharding blockchain protocols have sacrificed some important attributes to improve scalability, and this makes them complicated and insecure. Moreover, achieving a constant (rather than linear) Communication Cost Per Transaction (CCPT) is still a challenge for many sharding protocols. Motivated by this, we present EZchain, a scalable blockchain protocol via “passive sharding” with proven validity and security. We redesign the Value-Centric Blockchains (VCB) framework to achieve the passive sharding that helps EZchain reach higher security than traditional sharding protocols. With fixed initialization parameters, the expected value of EZchain's communication cost reaches a constant level, and it is independent of the network's size. Moreover, the EZchain node's storage cost without beacon chains also approaches a constant and does not change with the increase in the network's size and transactions. Cross-shard transactions, network sharding algorithm, and anti-Sybil attack verification are no longer needed in passive sharding, thus EZchain is very concise and efficient. Our experiment uses a lightweight EZchain prototype and extends the experimental network size up to 100,000 nodes. The evaluation results show that EZchain satisfies all our analyses of its performance (the constant communication and non-beacon storage cost) in large networks. In addition, the comparison experiment shows that ezchain has obvious advantages over the previous protocols in long-term operation and large network environments.

The exponential growth of data in the Internet of Vehicles (IoV) has created opportunities to improve traffic safety and efficiency through data trading. However, establishing trust among highly mobile and resource-constrained vehicles poses significant challenges for effective data trading in IoV. To address this issue, we propose a lightweight blockchain-based data trading scheme (LBDT), which ensures secure and efficient data trading in IoV. We introduce a proof-of-reputation (PoR) consensus mechanism to establish trustworthiness for data trading. Specifically, we use a progressive reputation mechainism to support the PoR consensus. LBDT utilizes a parallel-chain structure for the PoR consensus to minimize communication and storage costs while reducing transaction confirmation latency. Additionally, we adopt a double auction mechanism as an incentivizing strategy to encourage vehicle participation in data trading. We evaluate the performance of LBDT through extensive experiments. The experimental results demonstrate that LBDT is highly effective and secure, achieving a transaction latency of approximately 4 seconds. Moreover, LBDT successfully mitigates communication and storage overheads by over 90%, thus establishing its superiority over state-of-the-art solutions under comparable conditions.

We study online data analytics with differential privacy (DP) in decentralized settings. Specifically, online data analytics with local DP protection is widely adopted in real-world applications. Despite numerous endeavors in this field, significant gaps in utility and functionality remain when compared to its offline counterpart. We present an optimal, streamable mechanism:ExSub, for local DP sparse vector estimation. The mechanism enables a range of online analytics on streaming binary vectors, including multi-dimensional binary, categorical, or set-valued data. By leveraging the negative correlation of occurrence events in the sparse vector, we attain an optimal error rate under local privacy constraints, only requiring streamable computations. To surpass the error barrier of local privacy, we also studyExSubrandomizer in the newly emerging (single-message) shuffle model of DP, and provide nearly-tight privacy amplification bounds therein. Additionally, we leverage the online shuffle model that independently permutes users' messages at each timestamp, to design a simplified randomization strategy that can approximately reach Gaussian accuracy in central DP. Through experiments with both synthetic and real-world datasets,ExSubmechanism in the local model have been shown to reduce error by$40\%-60\%$compared to SOTA approaches. TheExSubin the shuffle model can further reduce over$85\%$error, and the online shuffle protocol reduces over$99.7\%$error.

Gait recognition plays a pivotal role in the area of mobile computing. While various research approaches leverage images, radar, RF signals, pressure sensors, wearables, and other methods, utilizing Wi-Fi signals for gait recognition offers distinct advantages such as a wide sensing range, simple deployment, and passive sensing capabilities. However, traditional gait recognition systems relying on Wi-Fi signals often suffer from performance degradation due to variations in walking directions and environmental conditions. To address this issue, in this paper we propose EIGait, a gait recognition system based on Wi-Fi signal time-frequency spectrograms. EIGait enhances the robustness and generalizability of extracted features through spectrogram augmentation, self-contrastive learning, and domain-adversarial training. Particularly, improvements to ResNet in EIGait yield a Spectrogram ResNet, which is better suited for time-frequency spectrograms. In addition, using merely a single pair of Wi-Fi transmitter and receiver, and by minimal signal denoising, we achieve the state-of-the-art performance. To evaluate the performance of EIGait, we conduct extensive experiments. In a typical indoor environment, EIGait achieves F1 scores ranging from 98.11% to 98.31% for four to eight individuals. In cross-direction gait recognition, we obtain F1 scores of 96.64% to 94.45% for four to eight individuals. Moreover, under the more challenging conditions of cross-room gait recognition, EIGait attains F1 scores of 92.09% to 89.61% for four to eight individuals. Additionally, we conduct experiments on the public dataset 3.0, and the results also demonstrate significant superiority.

As an essential computer vision task, Continual Semantic Segmentation (CSS) has received a lot of attention. However, security issues regarding this task have not been fully studied. To bridge this gap, we study the problem of attacks in CSS in this paper. We first propose a new task, namely, attacks on incremental samples in CSS, and reveal that the attacks on incremental samples corrupt the performance of CSS in both old and new classes. Moreover, we present an adversarial sample generation method based on class shift, namely Class Shift Attack (CS-Attack), which is an offline and easy-to-implement approach for CSS. CS-Attack is able to significantly degrade the performance of models on both old and new classes without knowledge of the incremental learning approach, which undermines the original purpose of the incremental learning, i.e., learning new classes while retaining old knowledge. Experiments show that on the popular datasets Pascal VOC, ADE20k, and Cityscapes, our approach easily degrades the performance of currently popular CSS methods, which reveals the importance of security in CSS.

Continual Semantic Segmentation (CSS) is an emerging trend, where catastrophic forgetting has been a perplexing problem. In this paper, we propose a Text-to-Image Knowledge Preservation (TIKP) framework to address this issue. TIKP applies Text-to-Image techniques to CSS by automatically generating prompts and content adaptation. It extracts associations between the labels of seen data and constructs text-level prompts based on these associations, which are preserved and maintained at each incremental step. During training, these prompts generate correlated images to mitigate the catastrophic forgetting. Particularly, as the generated images may have different distributions from the original data, TIKP transfers the knowledge by a content adaption loss, which determines the role played by the generated images in incremental training based on the similarity. In addition, for the classifier, we use the previous model from a different perspective: misclassifying new classes into old objects instead of the background. We propose a knowledge distillation loss based on wrong labels, enabling us to attribute varying weights to individual objects during the distillation process. Extensive experiments conducted in the same setting show that TIKP outperforms state-of-the-art methods by a large margin on benchmark datasets.

Generalizable NeRF can directly synthesize novel views across new scenes, eliminating the need for scene-specific re-training in vanilla NeRF. A critical enabling factor in these approaches is the extraction of a generalizable 3D representation by aggregating source-view features. In this paper, we propose an Entangled View-Epipolar Information Aggregation method dubbed EVE-NeRF. Differentfrom existing methods that consider cross-view and along-epipolar information independently, EVE-NeRF conducts the view-epipolar feature aggregation in an entangled manner by injecting the scene-invariant appearance continuity and geometry consistency priors to the aggregation process. Our approach effectively mitigates the potential lack of inherent geometric and appearance constraints resulting from one-dimensional interactions, thus further boosting the 3D representation generalizability. EVE-NeRF attains state-of-the-art performance across various evaluation scenarios. Extensive experiments demonstrate that, compared to pre-vailing single-dimensional aggregation, the entangled network excels in the accuracy of 3D scene geometry and appearance reconstruction. Our code is publicly available at https://github.com/tatakai1/EVENeRF.

Online data analytics with local privacy protection is widely adopted in real-world applications. Despite numerous endeavors in this field, significant gaps in utility and functionality remain when compared to its offline counterpart. This work demonstrates that private data analytics can be conducted online without excess utility loss, even at a constant factor. We present an optimal, streamable mechanism for local differentially private sparse vector estimation. The mechanism enables a range of online analytics on streaming binary vectors, including multi-dimensional binary, categorical, or set-valued data. By leveraging the negative correlation of occurrence events in the sparse vector, we attain an optimal error rate under local privacy constraints, only requiring streamable computations during the input’s data-dependent phase. Through experiments with both synthetic and real-world datasets, our proposals have been shown to reduce error rates by 40% to 60% compared to SOTA approaches.

Recent research has confirmed the possibility of adversarial attacks on deep models. However, these methods typically assume that the surrogate model has access to the target domain, which is difficult to achieve in practical scenarios. To address this limitation, this paper introduces a novel cross-domain attack method tailored for semantic segmentation, named Prototype-based Feature and Frequency Alteration Attack (PFFAA). This approach empowers a surrogate model to efficiently deceive the black-box victim model without requiring access to the target data. Specifically, through limited queries on the victim model, bidirectional relationships are established between the target classes of the victim model and the source classes of the surrogate model, enabling the extraction of prototypes for these classes. During the attack process, the features of each source class are perturbed to move these features away from their respective prototypes. Moreover, we propose substituting frequency information from images used to train the surrogate model into the frequency domain of the test images to modify texture and structure, thus further enhancing the attack efficacy. Experimental results across multiple datasets and victim models validate that PFFAA achieves state-of-the-art performances.

The shuffle model of differential privacy provides promising privacy-utility balances in decentralized, privacy-preserving data analysis. However, the current analyses of privacy amplification via shuffling lack both tightness and generality. To address this issue, we propose the variation-ratio reduction as a comprehensive framework for privacy amplification in both single-message and multi-message shuffle protocols. It leverages two new parameterizations: the total variation bounds of local messages and the probability ratio bounds of blanket messages, to determine indistinguishability levels. Our theoretical results demonstrate that our framework provides tighter bounds, especially for local randomizers with extremal probability design, where our bounds are exactly tight. Additionally, variation-ratio reduction complements parallel composition in the shuffle model, yielding enhanced privacy accounting for popular sampling-based randomizers employed in statistical queries (e.g., range queries, marginal queries, and frequent itemset mining). Empirical findings demonstrate that our numerical amplification bounds surpass existing ones, conserving up to 30% of the budget for single-message protocols, 75% for multi-message ones, and a striking 75%-95% for parallel composition. Our bounds also result in a remarkably efficient Õ ( n ) algorithm that numerically amplifies privacy in less than 10 seconds for n = 10 8 users.

Traditional machine learning-based steganalysis methods on compressed speech in VoIP applications have achieved great success. However, in these methods, there is a dilemma between the effectiveness of modeling the steganographic carrier and the high dimensionality of extracted features. Especially for small-sized and low embedding rate samples, most existing methods do not perform well enough. To deal with this issue, we present MDoIF— an Adaptive Multi-Rate (AMR) steganalysis of compressed speech based on multi-domain information fusion. In order to fully extract the information reflecting the change of carrier correlation before and after VoIP steganography, we construct a Bayesian network with FCB parameters in compressed speech as the vertices, and quantify link strength between codebook parameters. On this basis, we design a multi-domain feature extraction algorithm, supplemented by an information-theoretic measure-based feature selection algorithm for dimensionality reduction, which can significantly improve the performance of MDoIF. To evaluate the performance of our method, we conduct comprehensive experiments on MDoIF and existing models. Experimental results show that MDoIF performs effectively on various AMR steganalysis tasks with excellent detection accuracy. Particularly for small-sized and low embedding rate samples, MDoIF surpasses the state-of-the-art methods.

In many mobile applications, user-generated data are presented as set-valued data. To tackle potential privacy threats in analyzing these valuable data, local differential privacy has been attracting substantial attention. However, existing approaches only provide sub-optimal utility and are expensive in computation and communication for set-valued data distribution estimation and heavy-hitter identification. In this paper, we propose a utility-optimal and efficient set-valued data publication method (i.e.,Wheel mechanism). On the user side, the computational complexity is only$O(\min \lbrace m\log m, m e^\epsilon \rbrace )$and communication costs are$O(\epsilon +\log m)$bits, where$m$is the number of items,$d$is the domain size and$\epsilon$is the privacy budget, while existing approaches usually depend on$O(d)$or$O(\log d)$($d \gg m$). Our theoretical analyses reveal the estimation errors have been reduced from the previously known$O(\frac{m^{2} d}{n\epsilon ^{2}})$to the optimal rate$O(\frac{m d}{n\epsilon ^{2}})$. Additionally, for heavy-hitter identification, we present a variant of the Wheel mechanism as an efficient frequency oracle, entailing only$O(\sqrt{n})$computational complexity. This heavy-hitter protocol achieves an identification bar of$\tilde{O}(\frac{1}{\epsilon }\sqrt{\frac{m}{n} \log d})$, reducing by a factor of$\sqrt{m}$relative to existing protocols. Extensive experiments demonstrate our methods are 3-100x faster than existing approaches and have optimized statistical efficiency.

In recent years, deep learning-based approaches have shown great strength in multi-view stereo because of their outstanding ability to extract robust visual features. However, most learning-based methods need to build the cost volume and increase the receptive field enormously to get a satisfactory result when dealing with large-scale textureless regions, consequently leading to prohibitive memory consumption. To ensure both memory-friendly and textureless-resilient, we innovatively transplant the spirit of deformable convolution from deep learning into the traditional PatchMatch-based method. Specifically, for each pixel with matching ambiguity (termed unreliable pixel), we adaptively deform the patch centered on it to extend the receptive field until covering enough correlative reliable pixels (without matching ambiguity) that serve as anchors. When performing PatchMatch, constrained by the anchor pixels, the matching cost of an unreliable pixel is guaranteed to reach the global minimum at the correct depth and therefore increases the robustness of multi-view stereo significantly. To detect more anchor pixels to ensure better adaptive patch deformation, we propose to evaluate the matching ambiguity of a certain pixel by checking the convergence of the estimated depth as optimization proceeds. As a result, our method achieves state-of-the-art performance on ETH3D and Tanks and Temples while preserving low memory consumption.

Knowledge distillation has emerged as a scalable and effective way for privacy-preserving machine learning. One remaining drawback is that it consumes privacy in a client-level manner. In order to attain fine-grained privacy accountant and improve utility, this work proposes a model-free reverse k-NN labeling method towards record-level private knowledge distillation, where each private record is employed for labeling at most k queries. Theoretically, we provide bounds of labeling error rate under the centralized/local model of differential privacy. Experimentally, we demonstrate that it achieves new state-of-the-art accuracy in MNIST/SVHN/CIFAR-10 dataset with one order of magnitude lower of privacy loss.

There is an emerging effort to combine the two popular 3D frameworks using Multi-View Stereo (MVS) and Neural Implicit Surfaces (NIS) with a specific focus on the few-shot / sparse view setting. In this paper, we introduce a novel integration scheme that combines the multi-view stereo with neural signed distance function representations, which potentially overcomes the limitations of both methods. MVS uses per-view depth estimation and cross-view fusion to generate accurate surfaces, while NIS relies on a common coordinate volume. Based on this strategy, we propose to construct per-view cost frustum for finer geometry estimation, and then fuse cross-view frustums and estimate the implicit signed distance functions to tackle artifacts that are due to noise and holes in the produced surface reconstruction. We further apply a cascade frustum fusion strategy to effectively captures global-local information and structural consistency. Finally, we apply cascade sampling and a pseudo-geometric loss to foster stronger integration between the two architectures. Extensive experiments demonstrate that our method reconstructs robust surfaces and outperforms existing state-of-the-art methods.

To date, the boundary quality remains unsatisfactory in instance segmentation, resulting in increasing attention to the mask refinement mechanism. Such a mechanism is supposed to be accurate, efficient and generic to the existing models. Yet, few methods met the three factors simultaneously. In this paper, to address this issue, we propose a Boundary-Aware Prototype (BAProto) for boundary refinement, which conducts pixel-wise prediction through the similarity of boundary representation and the specific prototype. Such a prototype is obtained by a memory unit for comprehensive learning. To our best knowledge, BAProto is the first approach that satisfies the above three factors at the same time. In particular, we elaborately design a three-phase segmentation loss, focusing on the learning of different regions to extract discriminating boundary representations for prototype establishment. Extensive experimental results show that BAProto is precise, efficient and model-agnostic on COCO and Cityscapes datasets.

Current few-shot segmentation (FSS) approaches have made tremendous achievements based on prototypical learning techniques. However, due to the scarcity of the support data provided, FSS methods still suffer from the intra-class and inter-class gaps. In this paper, we propose a uniform network to fill both the gaps, termed FGNet. It consists of the novel design of a Self-Adaptive Module (SAM) to emphasize the query feature to generate an enhanced prototype for self-alignment. Such a prototype caters to each query sample itself since it contains the underlying intra-instance information, which gets around the intra-class appearance gap. Moreover, we design an Inter-class Feature Separation Module (IFSM) to separate the feature space of the target class from other classes, which contributes to bridging the inter-class gap. In addition, we present several new losses and a method termed B-SLIC, which help to further enhance the separation performance of FGNet. Experimental results show that FGNet reduces both the gaps for FSS by SAM and IFSM respectively, and achieves state-of-the-art performances on both PASCAL-5i and COCO-20i datasets compared with previous top-performing approaches.

In the field of object detector attacks, previous methods primarily rely on fixed gradient optimization or patch-based cover techniques, often leading to suboptimal attack performance and excessive distortions. To address these limitations, we propose a novel attack method, Interactive Reinforcement-based Sparse Attack (IRSA), which employs Reinforcement Learning (RL) to discover the vulnerabilities of object detectors and systematically generate erroneous results. Specifically, we formulate the process of seeking optimal margins for adversarial examples as a Markov Decision Process (MDP). We tackle the RL convergence difficulty through innovative reward functions and a composite optimization method for effective and efficient policy training. Moreover, the perturbations generated by IRSA are more subtle and difficult to detect while requiring less computational effort. Our method also demonstrates strong generalization capabilities against various object detectors. In summary, IRSA is a refined, efficient, and scalable interactive, iterative, end-to-end algorithm.

Blockchain technology has gained widespread use. However, it faces several challenges including throughput, transaction delay, security, and decentralization. This paper presents the Avalon protocol based on a novel Proof-of-Market (PoM) consensus mechanism to address these issues. PoM is a type of Proof-of-Work (PoW) consensus that incorporates market-driven leader election and shifts PoW from mining pools to consumers based on transactions. The matching incentive mechanism makes PoM incentive compatible. PoM decouples the scalability and security of Bitcoin, which means that Avalon can optimize the capacity and interval of blocks without compromising other performance goals. Our analysis shows that Avalon can tolerate malicious nodes possessing up to$\bf{1/3}$of the network's total computational power. Furthermore, the implementation of Avalon is similar to Bitcoin and is highly concise. We evaluate the performance of Avalon through a simulated network of over$\bf{1,000}$nodes. Experimental results demonstrate that Avalon can achieve a throughput of$\bf{4,000}$TPS (transactions per second), which is significantly better than state-of-the-art schemes ($\bf{10\boldsymbol{\times}}$Bitcoin-NG,$\bf{5\boldsymbol{\times}}$ByzCoin, and$\bf{4\boldsymbol{\times}}$Algorand). Additionally, it has a transaction confirmation delay of up to$\bf{40}$s, which is twice better than Bitcoin-NG and ByzCoin while experiencing only minimal blockchain splits and maintaining excellent decentralization.

Online service providers benefit from collecting and analyzing preference data from users, including both implicit preference data (e.g., watched videos of a user) and explicit preference data (e.g., ranking data over candidates). However, it brings ethical and legal issues of data privacy at the same time. In this paper, we study the problem of aggregating individual's preference data in the local differential privacy (LDP) setting. One naive approach is to add Laplace random noises, which however suffers from low statistical utility and is fragile to LDP-specific poisoning attacks. Therefore, we propose a novel mechanism to improve the utility and the robustness simultaneously: theadditive mechanism. The additive mechanism randomly outputs a subset of candidates with a probability proportional to their total scores. For preference data with Borda rule over$d$items, its mean squared error bound is optimized from$O(\frac{d^{5}}{n\epsilon ^{2}})$to$O(\frac{d^{4}}{n\epsilon ^{2}})$, and its maximum poisoning risk bound is reduced from$+\infty$to$O(\frac{d^{2}}{n\epsilon })$. We also theoretically investigate minimax lower bounds of$\epsilon$-LDP preference data aggregation, and prove the error rate of$O(\frac{d^{4}}{n\epsilon ^{2}})$is optimal for the Borda rule. Experimental results validate that our proposed approaches averagely reduce estimation error by 50% and are more robust to adversarial poisoning attacks.

Falling is a common health problem for elderly people. Early detection of falls allows earlier rescue measures to be implemented. Most existing Wi-Fi-based fall detection systems employ learning-based methods, which require large amounts of labeled data for prior training. To address this issue, we in this paper present AFall, a robust model-based fall detection system that does not require prior training for a single person based on Wi-Fi Channel State Information (CSI). Different from previous Wi-Fi-based fall detection systems, we model the relationship between human falls and changes of Angle of Arrival (AoA) of Wi-Fi signals reflected from human body by multiple signal classification (MUSIC) algorithm. In particular, we deploy two receivers in orthogonal spatial layouts to capture diversified AoA information. Since AoA reflected from human body is independent of environments and subjects, the performance of AFall can remain stable when the environment changes slightly, which can meet the daily needs of the elderly people. We implement AFall using commodity Wi-Fi devices and evaluate it in five different indoor environments. The experimental results demonstrate that AFall achieves an average accuracy of 84.31% and an average F1 score of 84.56%.

Currently, most of the mature WiFi-based step applications can only count the steps of a single individual, and their methods cannot capture amplitude information about each person's overall actions in multiuser scenes. It is still a challenging task to build a multiplayer step counting system in a device-free manner. In this paper, we present IMep, a novel device-free system based on WiFi that can obtain the amplitude information of each person's overall step actions and count the steps of multiple people simultaneously. Our main strategy is to establish a Multiplayer Stepping Amplitude Relation Model (MSARM) and design a Multiplayer Amplitude Decomposition Algorithm (MADA) that uses Block Term Decomposition (BTD). Moreover, we put forward a new Moving Energy Method (MEM) that captures each person's step number more clearly and accurately. The experimental results show that, IMep can function successfully in an environment of up to 7 people. The accuracies in three different room settings are 95.57%, 94.66%, and 89.94%, respectively, suggesting that IMep is effective in multi-person scenarios.

Smartphones have been the necessities for us due to their advanced computing capabilities and ubiquitous connectivity to our daily lives. However, they also produce many negative influences, such as ring noise, nuisance calls, which interrupt people’s attention when working. It would be user-friendly if smartphones can automatically sense the surroundings and dynamically work at an appropriate profile to prevent their ringing from disturbing people in some special circumstances. To address this issue, in this paper, we propose a novel smartphone profile switching system, called AutoProfile, which combines the techniques of acoustic sensing, walk detection and machine learning to automatically and dynamically change smartphones’ profiles in different scenarios. We develop a new compact ambient sound scheme for feature extraction, named DWT & MFCC fingerprint, which can effectively distinguish between different social scenarios and outperforms the existing method. To evaluate the performance of AutoProfile, we conduct experiments in 8 scenarios and take multiple influence factors into consideration. The results demonstrate that AutoProfile can realize overall recognition accuracies of$91.4 \;\%$and$90.6 \;\%$when using Random Forest and$k$-nearest Neighbors classifiers, respectively. Moreover, since AutoProfile senses the ambient sound passively, it does not create additional noise compared with some active acoustic sensing schemes. In addition, the power consumption of AutoProfile is acceptable, and thus AutoProfile can be tailored as a background service of smartphones to make them become “smarter”.

Bridging the advantages of differential privacy in both centralized model (i.e., high accuracy) and local model (i.e., minimum trust), the shuffle privacy model has potential applications in many privacy-sensitive scenarios, such as mobile user data aggregation and federated learning. Since messages from users are anonymized by semi-trusted shufflers (e.g., anonymous channels, edge servers), every user could hide message among other users’ messages and inject only part of noises (a.k.a. privacy amplification). However, existing works assume that the participating user population is known in advance, which is unrealistic for dynamic environments (e.g., mobile computing, vehicular networks). In this work, we study the shuffle privacy model with a random participating population, and give privacy amplification bounds for population size with commonly encountered binomial, Poisson, sub-Gaussian distribution and etc. For further improving accuracy, we formulate and derive optimal dummy sizes for both non-adaptive and adaptive dummies. Finally, to break the error barrier due to the constraint of sending one single message per user, we design a multi-message shuffle private protocol supporting random population. Experiment results show that our approaches reduce more than 60% error when compared to the local model and naive approaches. We hope this work provides tailored solutions of shuffle privacy for dynamic mobile/distributed computing.

Deep neural networks are extremely vulnerable to malicious input data. As 3D data is increasingly used in vision tasks such as robots, autonomous driving and drones, the internal robustness of the classification models for 3D point cloud has received widespread attention. In this paper, we propose a novel method named SPGA (Shape Prior Guided Attack) to generate adversarial point cloud examples. We use shape prior information to make perturbations sparser and thus achieve imperceptible attacks. In particular, we propose a Spatially Logical Block (SLB) to apply adversarial points through sliding in the oriented bounding box. Moreover, we design an algorithm called FOFA for this type of task, which further refines the adversarial attack in the process of breaking down complicated problems into sub-problems. Compared with the methods of global perturbation, our attack method consumes significantly fewer computations, making it more efficient. Most importantly of all, SPGA can generate examples with a higher attack success rate (even in a defensive situation), less perturbation budget and stronger transferability.

The training process of federated learning is known to be vulnerable to adversarial attacks (e.g., backdoor attack). Previous works showed that differential privacy (DP) can be used to defend against backdoor attacks, yet at the cost of vastly losing model utility. To address this issue, we in this paper propose a defense method based on differential privacy, called Clip Norm Decay (CND), to maintain utility when defending against backdoor attacks with DP. CND reduces the injected noise by decreasing the clipping threshold of model updates through the whole training process. In particular, our algorithm bounds the norm of malicious updates by adaptively setting the appropriate thresholds according to the current model updates. Empirical results show that CND can substantially enhance the accuracy of the main task when defending against backdoor attacks. Moreover, extensive experiments demonstrate that our method performs better defense than the original DP, further reducing the attack success rate, even in a strong assumption of threat model.

Current one-stage instance segmentation methods ignore the boundary information of masks, resulting in coarse masks that are far from the ground truth. In this paper, we propose a boundary-aware method to refine boundary information, called BSOLO. The core idea of BSOLO is to design a Hungarian-Algorithm-based boundary loss to calculate matching costs between boundaries. This loss effectively measures the difference between boundaries and suits for boundary regression, contributing to generating refined instance masks with high-quality boundaries. Besides, we propose a Feature Fusion Network (FFN) to capture long-range dependency. Through constructing the relationship between pixels, such a module is beneficial for predicting masks with large or uncontinuous region. Furthermore, we introduce a Prototype Attention Module (PAM) for mask assembling through channel attention, which enhances informative features and spotlights important prototypes. To evaluate the performance of BSOLO, we conduct extensive experiments. Experimental results show that BSOLO achieves 39.3 AP on MS COCO test-dev2017, outperforming SOLO and other methods by a large margin. We hope that BSOLO broadens the perspective for designing more valid boundary constraints.

Deep neural networks (DNNs) have lately shown tremendous performance in various applications. However, along-side their superiority in these tasks, recent studies have demon-strated that DNNs are easily fooled by adversarial attacks. To guard against adversarial examples, we provide a new solution to hardening DNNs through Block-term Dropout (BT-Dropout), an adversarial defense technique that leverages a latent high-order factorization of the network. Specifically, we impose low-rank block-term tensor structure on the weights of fully-connected layer to obtain compact networks, and then apply BT-Dropout in the latent subspace without pruning the weights directly. Meanwhile, for activation tensor fed into fully-connected layer, Tucker Dropout which can be viewed as a special case of BT-Dropout is introduced to preserve multilinear structure of activations. Furthermore, we show that BT-Dropout implicitly regularizes the tensor decomposition. Comprehensive experiments have demonstrated the effectiveness of our proposed method to improve the adversarial robustness for the models on standard image classification benchmarks.

Image generation from text is a challenging and ill-posed task. Images generated from previous methods usually have low semantic consistency with texts and the achieved resolution is limited. To generate semantically consistent high-resolution images, we propose a novel method named AtHom, in which two attention modules are developed to extract the relationships from both independent modality and unified modality. The first is a novel Independent Modality Attention Module (IAM), which is presented to find out semantically important areas in generated images and to extract the informative context in texts. The second is a new module named Unified Semantic Space Attention Module (UAM), which is utilized to find out the relationships between extracted text context and essential areas in generated images. In particular, to bring the semantic features of texts and images closer in a unified semantic space, AtHom incorporates a homomorphic training mode by exploiting an extra discriminator to distinguish between two different modalities. Extensive experiments show that our AtHom surpasses previous methods by large margins.

Existing self-supervised multi-view stereo (MVS) approaches largely rely on photometric consistency for geometry inference, and hence suffer from low-texture or non-Lambertian appearances. In this paper, we observe that adjacent geometry shares certain commonality that can help to infer the correct geometry of the challenging or low-confident regions. Yet exploiting such property in a non-supervised MVS approach remains challenging for the lacking of training data and necessity of ensuring consistency between views. To address the issues, we propose a novel geometry inference training scheme by selectively masking regions with rich textures, where geometry can be well recovered and used for supervisory signal, and then lead a deliberately designed cost volume completion network to learn how to recover geometry of the masked regions. During inference, we then mask the low-confident regions instead and use the cost volume completion network for geometry correction. To deal with the different depth hypotheses of the cost volume pyramid, we design a three-branch volume inference structure for the completion network. Further, by considering plane as a special geometry, we first identify planar regions from pseudo labels and then correct the low-confident pixels by high-confident labels through plane normal consistency. Extensive experiments on DTU and Tanks & Temples demonstrate the effectiveness of the proposed framework and the state-of-the-art performance.

Current multi-object tracking and segmentation (MOTS) methods follow the tracking-by-detection paradigm and adopt 2D or 3D convolutions to extract instance embeddings for instance association. However, due to the large receptive field of deep convolutional neural networks, the foreground areas of the current instance and the surrounding areas containing the nearby instances or environments are usually mixed up in the learned instance embeddings, resulting in ambiguities in tracking. In this paper, we propose a highly effective method for learning instance embeddings based on segments by converting the compact image representation to un-ordered 2D point cloud representation. In this way, the non-overlapping nature of instance segments can be fully exploited by strictly separating the foreground point cloud and the background point cloud. Moreover, multiple informative data modalities are formulated as point-wise representations to enrich point-wise features. For each instance, the embedding is learned on the foreground 2D point cloud, the environment 2D point cloud, and the smallest circumscribed bounding box. Then, similarities between instance embeddings are measured for the inter-frame association. In addition, to enable the practical utility of MOTS, we modify the one-stage instance segmentation method SpatialEmbedding for instance segmentation. The resulting efficient and effective framework, named PointTrackV2, outperforms all the state-of-the-art methods including 3D tracking methods by large margins (4.8 percent higher sMOTSA for pedestrians over MOTSFusion) with the near real-time speed (20 FPS evaluated on a single 2080Ti). Extensive evaluations on three datasets demonstrate both the effectiveness and efficiency of our method. Furthermore, as crowded scenes for cars are insufficient in current MOTS datasets, we provide a more challenging dataset named APOLLO MOTS with a much higher instance density.

With the increasing quantity of private cars, curb parking has evolved into an important approach to mitigate parking pressure in urban cities. While some efforts have been made for the demand analysis of point-of-interest (POI) and pattern analysis of human mobility, which may indirectly reflect the parking situation in urban area, there is a lack of comprehensive models for the parking demand, so as to make a prediction for the road sections without parking lots. In this paper, by focusing on curb parking and designing a systemic framework, namedCurb Parking Demand Estimation(CPDE), we model the public parking demand in urban area, w.r.t. parking durations and regional characteristics. Specifically, we use taxi destinations and the distribution of POIs to quantitatively analyze the regional characteristics, designing corresponding features, and propose aK-means-basedLeast Square (KLS) method to relate parking characteristics, namely, the temporal parking durations and the corresponding demands, with these features. In this way, we effectively avoid the geographical sparsity of road parking sections and can finely estimate parking durations and demands for newly developed districts without parking data. Moreover, we give a strategy, namedParking Types Estimation(PTE), which projects estimated parking durations and demands onto Gaussian Mixture Model (GMM) to accurately measure the distribution of demands over different parking durations for a road section. At last, we conduct experiments on a real-world curb parking dataset in Hefei, a provincial city in China. This dataset contains parking orders of 2016 over the urban area of Hefei. The experimental results validate the effectiveness of our methods, and show that our framework outperforms the state-of-the-art baseline schemes.

Cloud computing is motivating data owners to outsource their databases to the cloud. However, for privacy concerns, the sensitive data has to be encrypted before outsourcing, which inevitably posts a challenging task for effective data utilization. Existing work either focuses on keyword searches, or suffers from inadequate security guarantees or inefficiency. In this paper, we concentrate on multi-dimensional range queries over dynamic encrypted cloud data. We first propose a tree-based private range query scheme over dynamic encrypted cloud data (TRQED), which supports faster-than-linear range queries and protects single-dimensional privacy. Then, we discuss the defects of TRQED in terms of privacy-preservation. We modify the framework of the system by adopting a two-server model and put forward a safer range query scheme, called TRQED$^{+}$. By newly designed secure node query (SNQ) and secure point query (SPQ), we propose the perturbation-based oblivious R-tree traversal (ORT) operation to preserve both path pattern and stronger single-dimensional privacy. Finally, we conduct comprehensive experiments on real-world datasets and perform comparisons with existing works to evaluate the performance of the proposed schemes. Experimental results show that our TRQED and TRQED$^+$surpass the state-of-the-art methods in privacy-preservation level and efficiency.

Most existing Wi-Fi-based gait recognition systems consider gait cycle detection as a critical process. However, the noise mixed in dynamic measurements obtained from commercial Wi-Fi devices makes it hard to detect gait cycles. Herein, we adopt the attention-based Recurrent Neural Network (RNN) encoder-decoder and propose a cycle-independent human gait recognition and walking direction estimation system, termed AGait, in Wi-Fi networks. For capturing more human walking dynamics, two receivers together with one transmitter are deployed in different spatial layouts. The Channel State Information (CSI) from different receivers are first assembled and refined to form an integrated walking profile. Then, the RNN encoder reads and encodes the walking profile into primary feature vectors. Given a specific gait or direction sensing task, a corresponding and particular attention vector is computed by the decoder and is finally used to predict the target. The attention scheme motivates AGait to learn to adaptively align with different critical clips of CSI data for different tasks. We implement AGait on commercial Wi-Fi devices in three different indoor environments, and the experimental results demonstrate that AGait can achieve average$F_1$scores of 97.32 to 89.77 percent for gait recognition from a group of 4 to 10 subjects and 97.41 percent for direction estimation from 8 walking directions.

In the age of 5G, everything is connected. The departure site, destination site, departure time and other information of all vehicles on the road can be known by the unified dispatching center. Therefore, on this basis, the vehicle routing model in the traffic network is established. In the scheduling model, the real world vehicle driving situation is simulated by setting the road vehicle scheduling strategy and the intersection passing strategy. By considering the deadlock state, the problem of priority of vehicles passing through the intersection is solved. Considering the congestion in the road and the frequent use of the road in the network center, the whole road grid is layered. The heuristic algorithm with path congestion is used to calculate the route selection of vehicles in real time. The experimental results show that the total scheduling time and waiting time can be effectively reduced when the route scale and vehicle scale are large.

In this paper, we propose VK-Net, a neural network that learns to discover a set of category-specific keypoints from a single point cloud in an unsupervised manner. VK-Net is able to generate semantically consistent and rotation invariant keypoints across objects of the same category and different views. Particularly, we find that utilizing learned keypoints for the task of point cloud registration outperforms other traditional and learning-based approaches. Given the paired source and target point clouds, we can construct keypoint correspondences from learned keypoints using VK-Net. These keypoint correspondences are then employed to calculate a good pose initialization, after which an ICP is utilized to refine the registration. Extensive experiments on the ShapeNet dataset demonstrate that our model outperforms the state-of-the-art methods by a large margin.

Current light field (LF) occlusion removal approaches usually select only a part of sub-aperture images (SAIs) or simply stack all SAIs to reconstruct the center view, which destroys the spatial layout of SAIs. In this paper, we present a simple yet effective LF occlusion removal method name Mask4D, which is a 4D convolution-based encoder-decoder network. We propose to keep the spatial layout of SAIs and construct all SAIs as a 5D input tensor to fully exploit the spatial connection information between SAIs. In particular, except for center view reconstruction, we jointly predict the occlusion mask to disentangle the occlusion mask from the occluded content. Extensive evaluations demonstrate that our Mask4D surpasses the state-of-the-art approaches across different datasets. Moreover, visualizations show that Mask4D predicts the occlusion mask precisely and the reconstructed center view looks more realistic than other approaches. Our code will be publicly available.

Deep convolutional neural networks are widely witnessed vulnerable to adversarial attacks. Recently, great progress has been achieved in attacking object detectors. However, current attacks neglect the practical utility and rely on global perturbations on the target image with a large number of patches or pixels. In this paper, we present a novel attack framework named DTTACK to fool both one-stage and two-stage object detectors with limited perturbations. A novel divergent patch shape consisting of four intersecting lines is proposed to effectively affect deep convolutional feature extraction with limited pixels. In particular, we introduce an instance-aware heat map as a self-attention module to help DTTACK focus on salient object areas, which further improves the attacking performance. Extensive experiments on PASCAL-VOC, MS-COCO, as well as an online detection system demonstrate that DTTACK surpasses the state-of-the-art methods by large margins.

Human activity recognition is an essential part of human-computer interaction systems. Environment-robust Wi-Fi-based systems for this task is still a challenging problem, due to the fact that most existing systems may drop in performance when the environment is changed. To address this issue, we in this paper present WiHARAN, a Wi-Fi-based activity recognition system that can learn environment-independent features from Channel State Information (CSI) traces. With a well-designed base network capable of extracting temporal information from spectrograms, we align the joint distribution of features and labels from multiple environments utilizing adversarial learning. Experimental results show that our system achieves better performance than state-of-the-art solutions and can improve performance in difficult environments.

Current text spotting methods perform text detection and text recognition separately. However, in complex scenes where bounding boxes of texts with various shapes are often overlapped, text detection becomes error-prone. By contrast, character detection is more non-ambiguous and easier to learn. In this paper, we present a highly efficient one-stage method named PointerNet for arbitrary-shaped text spotting. Unlike previous methods, PointerNet does not rely on text detection and opens a novel spotting-by-character-detection paradigm. In particular, to connect characters to texts, we propose a simple yet highly effective strategy named pointer that learns the 2D offset from the center of the current character to the center of the subsequent character. Evaluations demonstrate that our PointerNet achieves state-of-the-art performance and is more efficient than current methods (75ms vs. 133ms compared with FOTS). Our code will be publicly available.

Current self-supervised depth estimation algorithms mainly focus on either stereo or monocular only, neglecting the reciprocal relations between them. In this paper, we propose a simple yet effective framework to improve both stereo and monocular depth estimation by leveraging the underlying complementary knowledge of the two tasks. Our approach consists of three stages. In the first stage, the proposed stereo matching network termed StereoNet is trained on image pairs in a self-supervised manner. Second, we introduce an occlusion-aware distillation (OA Distillation) module, which leverages the predicted depths from StereoNet in non-occluded regions to train our monocular depth estimation network named SingleNet. At last, we design an occlusion-aware fusion module (OA Fusion), which generates more reliable depths by fusing estimated depths from StereoNet and SingleNet given the occlusion map. Furthermore, we also take the fused depths as pseudo labels to supervise StereoNet in turn, which brings StereoNet’s performance to a new height. Extensive experiments on KITTI dataset demonstrate the effectiveness of our proposed framework. We achieve new SOTA performance on both stereo and monocular depth estimation tasks.

Current one-step multi-object tracking and segmentation (MOTS) methods lag behind recent two-step methods. By separating the instance segmentation stage from the tracking stage, two-step methods can exploit non-video datasets as extra data for training instance segmentation. Moreover, instances belonging to different IDs on different frames, rather than limited numbers of instances in raw consecutive frames, can be gathered to allow more effective hard example mining in the training of trackers. In this paper, we bridge this gap by presenting a novel data augmentation strategy named continuous copy-paste (CCP). Our intuition behind CCP is to fully exploit the pixel-wise annotations provided by MOTS to actively increase the number of instances as well as unique instance IDs in training. Without any modifications to frameworks, current MOTS methods achieve significant performance gains when trained with CCP. Based on CCP, we propose the first effective one-stage online MOTS method named CCPNet, which generates instance masks as well as the tracking results in one shot. Our CCPNet surpasses all state-of-the-art methods by large margins (3.8% higher sMOTSA and 4.1% higher MOTSA for pedestrians on the KITTI MOTS Validation) and ranks 1st on the KITTI MOTS leaderboard. Evaluations across three datasets also demonstrate the effectiveness of both CCP and CCPNet. Our codes are publicly available at: https://github.com/detectRecog/CCP.

Depth completion aims to recover the dense depth map from sparse depth data and RGB image respectively. However, due to the huge difference between the multi-modal signal input, vanilla convolutional neural network and simple fusion strategy cannot extract features from sparse data and aggregate multi-modal information effectively. To tackle this problem, we design a novel network architecture that takes full advantage of multi-modal features for depth completion. An effective Pre-completion algorithm is first put forward to increase the density of the input depth map and to provide distribution priors. Moreover, to effectively fuse the image features and the depth features, we propose a multi-modal deep aggregation block that consists of multiple connection and aggregation pathways for deeper fusion. Furthermore, based on the intuition that semantic image features are beneficial for accurate contour, we introduce the deformable guided fusion layer to guide the generation of the dense depth map. The resulting architecture, called MDANet, outperforms all the stateof-the-art methods on the popular KITTI Depth Completion Benchmark, meanwhile with fewer parameters than recent methods. The code of this work will be available at https://github.com/USTC-Keyanjie/MDANet_ICRA2021.

Numerical vector aggregation has numerous applications in privacy-sensitive scenarios, such as distributed gradient estimation in federated learning, and statistical analysis on key-value data. Within the framework of local differential privacy, this work gives tight minimax error bounds of O(d s/(n epsilon^2)), where d is the dimension of the numerical vector and s is the number of non-zero entries. An attainable mechanism is then designed to improve from existing approaches suffering error rate of O(d^2/(n epsilon^2)) or O(d s^2/(n epsilon^2)). To break the error barrier in the local privacy, this work further consider privacy amplification in the shuffle model with anonymous channels, and shows the mechanism satisfies centralized (14 ln(2/delta) (s e^epsilon+2s-1)/(n-1))^0.5, delta)-differential privacy, which is domain independent and thus scales to federated learning of large models. We experimentally validate and compare it with existing approaches, and demonstrate its significant error reduction.

While machine learning brings convenience, it also faces the issue of data privacy. For privacy issues, most researches focus on implementing homomorphic encryption or differential privacy to protect data, while ignoring the potential threats caused by the leakage of model parameters. However, a malicious attacker can still recover sensitive data information through model parameters. On the one hand, traditional methods cannot take both high accuracy and low computation time into account. On the other hand, they cannot resist the reconstruction attack from the model's parameter. In order to address this problem, this paper designs a privacy protection framework named FLI, which is inspired by public key infrastructure. In FLI, all participants and the server are trained and aggregated under one framework based on federated learning, which includes key exchange and shares with the idea of homomorphic encryption. Under the algorithm we design, the malicious adversary cannot recover effective information after obtaining the transformed parameters, while the server can still perform effective parameter aggregation. To evaluate the performance of FLI, we conduct extensive experiments. The experimental results show that the computation time is within an acceptable range while ensuring high accuracy.

In this paper, we propose a dimension apart network (DANet) for radar object detection task. A Dimension Apart Module (DAM) is first designed to be lightweight and capable of extracting temporal-spatial information from the RAMap sequences. To fully utilize the hierarchical features from the RAMaps, we propose a multi-scale U-Net style network architecture termed DANet. Extensive experiments demonstrate that our proposed DANet achieves superior performance on the radar detection task at much less computational cost, compared to previous pioneer works. In addition to the proposed novel network, we also utilize a vast amount of data augmentation techniques. To further improve the robustness of our model, we ensemble the predicted results from a bunch of lightweight DANet variants. Finally, we achieve 82.2% on average precision and 90% on average recall of object detection performance and rank at 1st place in the ROD2021 radar detection challenge. Our code is available at: \urlhttps://github.com/jb892/ROD2021_Radar_Detection_Challenge_Baidu.

Without appealing to exhaustive labeled data, self-supervised monocular depth estimation (MDE) plays a fundamental role in computer vision. Previous methods usually adopt a one-stage MDE network, which is insufficient to achieve high performance. In this paper, we dig deep into this task to propose an aggressive framework termed AggNet. The framework is based on a training-only progressive two-stage module to perform pseudo counter-surveillance as well as a simple yet effective dual-warp loss function between image pairs. In particular, we first propose a residual module, which follows the MDE network to learn a refined depth. The residual module takes both the initial depth generated from MDE and the initial color image as input to generate refined depth with residual depth learning. Then, the refined depth is leveraged to supervise the initial depth simultaneously during the training period. For inference, only the MDE network is retained to regress depth from a single image, which gains better performance without introducing extra computation. In addition to self-distillation loss, a simple yet effective dual-warp consistency loss is introduced to encourage the MDE network to keep depth consistency between stereo image pairs. Extensive experiments show that our AggNet achieves state-of-the-art performance on the KITTI and Make3D datasets.

Existing Few Shot Segmentation (FS-Seg) methods mostly study a restricted setting where only foreground and background are required to be discriminated and fall short at discriminating multiple classes. In this paper, we focus on a challenging but more practical variant: Generalized Few Shot Segmentation (GFS-Seg), where all SEEN and UNSEEN classes are segmented simultaneously. Previous methods treat the background as a regular class, leading to difficulty in differentiating UNSEEN classes from it at the test stage. To address this issue, we propose Adaptive Background Modeling and Prototype Query Network (ABPNet), in which the background is formulated as the complement of the set of interested classes. With the help of the attention mechanism and a novel meta-training strategy, it learns an effective set difference function that predicts task-specific background adaptively. Furthermore, we design a Prototype Querying (PQ) module that effectively transfers the learned knowledge to UNSEEN classes with a neural dictionary. Experimental results demonstrate that ABPNet significantly outperforms the state-of-the-art method CAPL on PASCAL-5i and COCO-20i, especially on UNSEEN classes. Also, without retraining, ABPNet can generalize well to FS-Seg.

Traditional machine learning-based steganalysis methods on compressed speech have achieved great success in the field of communication security. However, previous studies lacked mathematical modeling of the correlation between codewords, and there is still room for improvement in steganalysis for small-sized and low embedding rate samples. To deal with the challenge, we use Bayesian networks to measure different types of correlations between codewords in linear prediction code and present F3SNet—a four-step strategy: embedding, encoding, attention, and classification for quantization index modulation steganalysis of compressed speech based on the hierarchical attention network. Among them, embedding converts codewords into high-density numerical vectors, encoding uses the memory characteristics of LSTM to retain more information by distributing it among all its vectors, and attention further determines which vectors have a greater impact on the final classification result. To evaluate the performance of F3SNet, we make a comprehensive comparison of F3SNet with existing steganography methods. Experimental results show that F3SNet surpasses the state-of-the-art methods, particularly for small-sized and low embedding rate samples.

3D object detection is an essential task in autonomous driving and robotics. Though great progress has been made, challenges remain in estimating 3D pose for distant and occluded objects. In this paper, we present a novel framework named ZoomNet for stereo imagery-based 3D detection. The pipeline of ZoomNet begins with an ordinary 2D object detection model which is used to obtain pairs of left-right bounding boxes. To further exploit the abundant texture cues in rgb images for more accurate disparity estimation, we introduce a conceptually straight-forward module – adaptive zooming, which simultaneously resizes 2D instance bounding boxes to a unified resolution and adjusts the camera intrinsic parameters accordingly. In this way, we are able to estimate higher-quality disparity maps from the resized box images then construct dense point clouds for both nearby and distant objects. Moreover, we introduce to learn part locations as complementary features to improve the resistance against occlusion and put forward the 3D fitting score to better estimate the 3D detection quality. Extensive experiments on the popular KITTI 3D detection dataset indicate ZoomNet surpasses all previous state-of-the-art methods by large margins (improved by 9.4% on APbv (IoU=0.7) over pseudo-LiDAR). Ablation study also demonstrates that our adaptive zooming strategy brings an improvement of over 10% on AP3d (IoU=0.7). In addition, since the official KITTI benchmark lacks fine-grained annotations like pixel-wise part locations, we also present our KFG dataset by augmenting KITTI with detailed instance-wise annotations including pixel-wise part location, pixel-wise disparity, etc.. Both the KFG dataset and our codes will be publicly available at https://github.com/detectRecog/ZoomNet.

Generative Adversarial Network (GAN) has already made a big splash in the field of generating realistic "fake" data. However, when data is distributed and data-holders are reluctant to share data for privacy reasons, GAN’s training is difficult. To address this issue, we propose private FL-GAN, a differential privacy generative adversarial network model based on federated learning. By strategically combining the Lipschitz limit with the differential privacy sensitivity, the model can generate high-quality synthetic data without sacrificing the privacy of the training data. We theoretically prove that private FL-GAN can provide strict privacy guarantee with differential privacy, and experimentally demonstrate our model can generate satisfactory data.

Attributed graph data is powerful to describe relational information in various areas, such as social links through numerous web services and citation/reference relations in the collaboration network. Taking advantage of attributed graph data, service providers can model complex systems and capture diversified interactions to achieve better business performance. However, privacy concern is a huge obstacle to collect and analyze user's attributed graph data. Existing studies on protecting private graph data mainly focus on edge local differential privacy(LDP), which might be insufficient in some highly sensitive scenarios. In this paper, we present a novel privacy notion that is stronger than edge LDP, and investigate approaches to analyze attributed graphs under this notion. To neutralize the effect of excessively introduced noise, we propose PrivAG, a privacy-preserving framework that protects attributed graph data in the local setting while providing representative graph statistics. The effectiveness and efficiency of PrivAG framework is validated through extensive experiments.

6DoF object pose estimation is essential for many real-world applications. Although great progress has been made, challenges still remain in estimating 6D pose for occluded objects. Current RGB-D approaches predict 6DoF pose directly, which is sensitive to occlusion in cluttered scenes. In this work, we propose DCNet, an end-to-end framework for estimating 6DoF object poses. DCNet first converts pixels in the image plane to point clouds in the camera coordinate system and then establishes dense correspondences between the camera coordinate system and the object coordinate system. Based on these two systems, we fuse 2D appearance and 3D geometric features by pixel-wise concatenation to construct dense correspondences, from which the pose is calculated through the least-squares fitting algorithm. Dense correspondences guarantee enough point pairs for a robust 6DoF pose estimation, even if the occlusion is heavy. Experimental results demonstrate that DCNet outperforms the state-of-the-art methods on LINEMOD, Occlusion LINEMOD and YCB-Video datasets, especially in terms of the robustness to occlusion scenes.

Most user-generated data in online services are presented as set-valued data, e.g., visited website URLs, recently used Apps by a person, and etc. These data are of great value to service providers, but also bring privacy concerns if collected and analyzed directly. To tackle potential privacy threatens, local differential privacy (LDP) attracts increasing attention nowadays. However, existing approaches only provide sub-optimal error bound for set-valued data distribution estimation with LDP. Besides, it is computational expensive and communication expensive to use for high dimensional set-valued data, considering large domains in real scenarios. Thus, existing approaches are unpractical to use on resource-constrained user-side devices (e.g., smartphones and wearable devices). In this paper, we propose a utility-optimal and efficient set-valued data publication method (i.e., wheel mechanism ). On the user side, each user contributes only one numerical value to represent their privatized data. The computational complexity is O (min{ m log m , me ɛ }) and communication cost is O (log( me ɛ )) bits, while existing approaches usually depend on O ( d ) or O (log d ), where m is the number of items in the set-valued data ( m ≡ 1 for categorical data), d is the domain size (usually d ≫ m ) and ɛ is the privacy budget. On the server side, the estimator takes numerical values from users as input and derives an unbiased distribution estimation. Theoretical results show that estimation error bounds are improved from previously known [EQUATION] to the optimal rate [EQUATION]. Results on extensive experiments demonstrate that our proposed wheel mechanism is 3-100× faster than existing approaches, meanwhile has optimal statistical efficiency.

On-Line Analytical Processing (OLAP) enables powerful analytics by quickly computing aggregate values of numerical measures over multiple hierarchical dimensions for massive datasets. However, many types of source data, e.g., from GPS, sensors, and other measurement devices, are intrinsically inaccurate (imprecise and/or uncertain) and thus OLAP cannot be readily applied. In this paper, we address the resulting data veracityproblem in OLAP by proposing the concept of probabilistic data cubes. Such a cube is comprised of a set of probabilistic cuboids which summarize the aggregated values in the form of probability mass functions (pmfs in short) and thus offer insights into the underlying data quality and enable confidence-aware query evaluation and analysis. However, the probabilistic nature of data poses computational challenges, since a probabilistic database can have exponential number of possible worlds under the possible world semantics. Even worse, it is hard to share computations among different cuboids, as aggregation functions that are distributive for traditional data cubes, e.g., SUM, become holistic in probabilistic settings. In this paper, we propose a complete set of techniques for probabilistic data cubes, from cuboid aggregation, over cube materialization, to query evaluation. We study two types of aggregation: convolution and sketch-based, which take polynomial time complexities for aggregation and jointly enable efficient query processing. Also, our proposal is versatile in terms of: 1) its capability of supporting common aggregation functions, i.e., SUM, COUNT, MAX, and AVG; 2) its adaptivity to different materialization strategies, e.g., full versus partial materialization, with support of our devised cost models and parallelization framework; 3) its coverage of common OLAP operations, i.e., probabilistic slicing and dicing queries. Extensive experiments over real and synthetic datasets show that our techniques are effective and scalable.

As information security is increasingly valued, privacy-preserving data mining has become a research hotspot in the field of big data and signal processing. We propose a new differentially private greedy decision forest algorithm called DPGDF to help improve the accuracy of privacy-preserving data mining. Unlike previous algorithms that only employed greedy decision trees or random forests, our algorithm uses a combination of greedy trees and parallel combination theory to construct a greedy decision forest and coordinate privacy protection and prediction accuracy to achieve the best balance. Combined with smooth sensitivity, the introduction of noise is minimized, making the prediction accuracy of the algorithm notably better than the current state-of-the-art algorithms. Experiments on the UCI datasets show that the prediction accuracy of our algorithm is about 10% higher than that of those algorithms.

Local differential privacy (LDP), as a strong and practical notion, has been applied to deal with privacy issues in data collection. However, existing LDP-based strategies mainly focus on utility optimization at a single privacy level while ignoring various privacy preferences of data providers and multilevel privacy demands for statistics. In this poster, we for the first time propose a framework to optimize the utility of histogram estimation with these two privacy requirements. To clarify the goal of privacy protection, we personalize the traditional definition of LDP. We design two independent approaches to minimize the utility loss: Advanced Combination, which composes multilevel results for utility optimization, and Data Recycle with Personalized Privacy, which enlarges sample size for an estimation. We demonstrate their effectiveness on privacy and utility. Moreover, we embed these approaches within a Recycle and Combination Framework and prove that the framework stably achieves the optimal utility by quantifying its error bounds. On real-world datasets, our approaches are experimentally validated and remarkably outperform baseline methods.

Recently, local differential privacy (LDP), as a strong and practical notion, has been applied to deal with privacy issues in data collection. However, existing LDP-based strategies mainly focus on utility optimization at a single privacy level while ignoring various privacy preferences of data providers and multilevel privacy demands for statistics. In this paper, we for the first time propose a framework to optimize the utility of histogram estimation with these two privacy requirements. To clarify the goal of privacy protection, we personalize the traditional definition of LDP. We design two independent approaches to minimize the utility loss: Advanced Combination, which composes multilevel results for utility optimization, and Data Recycle with Personalized Privacy, which enlarges the sample size for an estimation. We demonstrate their effectiveness on privacy and utility, respectively. Moreover, we embed these approaches within a Recycle and Combination Framework and prove that the framework stably achieves the optimal utility by quantifying its error bounds. On real-world datasets, our approaches are experimentally validated and remarkably outperform baseline methods.

For the purpose of improving the quality of services, softwares or online services are collecting various of user data, such as personal information and locations. Such data facilitates mining statistical knowledge of users, but threatens users' privacy as it may reveal sensitive information (e.g., identities and activities) about individuals. This work considers distribution estimation over user-contributed data meanwhile providing rigid protection of their data with local ε-differential privacy (ε-LDP), which sanitizes each user's data on the client's side (e.g, on the user's mobile device). Our privacy protection covers both qualitative data (e.g., categorical data) and discrete quantitative data (e.g., location data). Specifically, for categorical data, we derive an optimal ε-LDP mechanism (termed as k-subset mechanism) from mutual information perspective, and further show its optimality over existing approaches within the context of discrete distribution estimation; for discrete quantitative data that have arbitrary distance metric, we provide an efficient extension of k-subset mechanism by proposing a variant of the popular Exponential Mechanism (EM) to tackle the asymmetry issue on the data domain. Experiments on real-world datasets and simulated scenarios show that our mechanism is highly efficient and reduces nearly a fraction of exp(- ε/2) error for distribution estimation when compared to existing approaches.

Traditional word embedding approaches learn semantic information at word level while ignoring the meaningful internal structures of words like morphemes.Furthermore, existing morphology-based models directly incorporate morphemes to train word embeddings, but still neglect the latent meanings of morphemes.In this paper, we explore to employ the latent meanings of morphological compositions of words to train and enhance word embeddings.Based on this purpose, we propose three Latent Meaning Models (LMMs), named LMM-A, LMM-S and LMM-M respectively, which adopt different strategies to incorporate the latent meanings of morphemes during the training process.Experiments on word similarity, syntactic analogy and text classification are conducted to validate the feasibility of our models.The results demonstrate that our models outperform the baselines on five word similarity datasets.On Wordsim-353 and RG-65 datasets, our models nearly achieve 5% and 7% gains over the classic CBOW model, respectively.For the syntactic analogy and text classification tasks, our models also surpass all the baselines including a morphology-based model.

With the rapid development of mobile technologies, LTE is turning to be a wonderful carrier for covert channels. Existing detection for covert storage channel (CSC) are almost packet analysis based methods. In this paper, we present an entropy-based method for detecting CSC in Sequence Number (SN) fields of PDCP and RLC layer, which is seen as the most difficult to be detected. We simulate the LTE network in NS3 platform, and propose a Protocol Data Unit (PDU) based blind method to calculate the distance between the SN of PDU and its first left neighbor, instead of analyzing the packets or extracting the value of SN from the PDU. Our experimental results have demonstrated that the proposed detection method is sensitive to the hidden information in the SN fields of PDCP and RLC layer. It can detect them in an accurate manner, and can be conducted in both real-time online and offline storage detection.

License plate recognition is an essential step in automatic license plate recognition since it is a key technology to recognize detected license plates. Though there are extensive researches on license plate recognition, it is still challenging to recognize license plates under conditions like great tilt angles, uneven illuminations, and distortions. Based on the observation that an accurate shape correction can significantly improve the recognition accuracy on these images, this paper proposes a robust methodology named LCR for license plate recognition free of conventional image analysis operations. This approach is based on three neural networks for three different purposes: (i) predicting the locations of four vertices; (ii) predicting cutting locations; (iii) character classification. To the best of our knowledge, LCR is the first to address shape correction by designing neural networks to accurately predict the coordinates of license plates vertices. Experiments on over 250,000 unique images show that LCR significantly outperforms several state-of-the-art license plate recognition approaches. Moreover, in evaluations, the application of shape correction significantly improve the recognition accuracy.

Set-valued data is useful for representing a rich family of information in numerous areas, such as market basket data of online shopping, apps on mobile phones and web browsing history. By analyzing set-valued data that are collected from users, service providers could learn the demographics of the users, the patterns of their usages, and finally, improve the quality of services for them. However, privacy has been an increasing concern in collecting and analyzing users' set-valued data, since these data may reveal sensitive information (e.g., identities, preferences and diseases) about individuals. In this work, we propose a privacy preserving aggregation mechanism for set-valued data: PrivSet. It provides rigorous data privacy protection locally (e.g., on mobile phones or wearable devices) and efficiently (its computational overhead is linear to the item domain size) for each user, and meanwhile allowing effective statistical analyses (e.g., distribution estimation of items, distribution estimation of set cardinality) on set-valued data for service providers. More specifically, in PrivSet, within the constraints of local e-differential privacy, each user independently responses with a subset of the set-valued data domain with calibrated probabilities, hence the true positive/false positive rate of each item is balanced and the performance of distribution estimation is optimized. Besides presenting theoretical error bounds of PrivSet and proving its optimality over existing approaches, we experimentally validate the mechanism, the experimental results illustrate that the estimation error in PrivSet has been reduced by half when compared to state-of-the-art approaches.

For online conversations with top privacy, we often need to erase the existing contact behavior. Thus we want communications in which adversaries can not link you to the person you contact, namely communications with unlinkability. However, most current communication systems including variations of Mix networks fail to maintain unlinkability against global active adversaries (GAA) who can monitor global traffic and easily compromise clients and infrastructures. Therefore, designing an unlinkable communication system against GAA is challenging. By analyzing limitations of current communication systems, we propose two other features to assure unlinkability: covertness and deniability. In this paper, we design HTor, a novel and practical communication system with unlinkability, via a single web server. HTor interpolates the server to cut off the direct connection between two people in one communication and exploits covert channels (CCs) to hide communications between clients and the server. Considering servers might be corrupted, HTor utilizes a group mechanism to protect the receiver for each message. By extensive large-scale evaluations, we show that communications over HTor are robust and difficult to detect. Besides, HTor is easily implemented and, with multiple servers, it can provide enough bandwidth and relatively low latency for chatting.

Covert channels transmit secret information by using the existing resources which were not designed for communication. As a major approach to information leakage, covert channels are rapidly gaining popularity with the exponentially growth of cloud and network resources. Long Term Evolution Advance (LTE‐A) has dominated the mobile telecommunication networks, which brings an elevation of the risk of covert channels. In this study, the authors propose a supervised learning scheme based on support vector machine (SVM) for the covert channel detection in LTE‐A. Based on the fact that the covert channel using the header fields of LTE‐A protocol would change the regularity, goodness of fit or correlation of the data traffic, they present behaviour characteristics statistics index (CSI) in the LTE‐A protocol to evaluate the changes. According to CSI, they extract the classification feature vectors from the data traffic stream, based on which an SVM classifier used for classifying the channel as covert or overt is trained for testing on the channel under investigation. Experiment results show that the authors' proposed detection scheme is high‐efficiency in terms of detection accuracy, sensitivity and specificity, which has great potential to serve as a new idea for the detection of covert channel in LTE‐A.

With the increasing prevalence of cloud computing, data owners prefer to outsource their databases to the cloud. For the protection of data privacy, sensitive data have to be encrypted before outsourcing, which introduces much difficulty into effective data utilization. Most previous studies either suffer from privacy disclosure and low efficiency, or do not support personalized multidimensional range queries. In this paper, we focus on personalized private range queries over outsourced data. We propose a personalized and privacy-preserving private range query protocol (PPP), which uses bounding-box PIR (bbPIR) to trade access pattern privacy for flexible privacy and high efficiency, and satisfies various quality of service (QoS) requirements. To our best knowledge, PPP is the first to achieve personalized search according to owner-specified privacy-cost tradeoff. Furthermore, PPP is secure against semi-honest adversaries under known ciphertext model. Experimental results on real-world datasets show that PPP is efficient and able to achieve diverse QoS requirements.

The categorical data that have natural ordering between categories are termed ordinal data, which are pervasive in numerous areas, including discrete sensor readings, metering data or preference options. Though aggregating such ordinal data from the population is facilitating plenty of crowdsourcing applications, contributing such data is privacy risky and may reveal sensitive information (e.g. locations, identities) about individuals. This work studies ordinal data aggregation for distribution estimation meanwhile locally preserving individuals' data privacy (such as on their mobile devices). Under ε-geo-indistinguishable constraints, which capture intrinsic dissimilarity between ordinal categories in the framework of differential privacy, we provide an efficient and effective locally private mechanism: Subset Exponential Mechanism (SEM) for ordinal data distribution estimation. The mechanism randomly responds with a fixed-size subset of the categories with calibrated probability assignment. Specially for uniform ordinal data, we propose a circling technique to symmetrically randomizing categories and estimating frequencies of categories, hence the computational/space costs and estimation performance of SEM are further optimized. Besides contributing theoretical error bounds of SEM, we also evaluate the mechanism on extensive scenarios, the evaluation results show that SEM reduces distribution estimation error on average by exp(ϵ/2) factor over existing private mechanisms.

Time synchronisation is a fundamental requirement for the IEEE802.15.4e‐based industrial Internet of Things, allowing it to reach low‐power and high‐reliability wireless network through time synchronisation. If malicious adversaries launch time synchronisation attacks to IEEE802.15.4e‐based networks, the entire network communication will be paralysed. In this study, the authors introduce two types of time synchronisation attacks: (i) absolute slot number (ASN) and (ii) timeslot template attack. In ASN attack, the new nodes may receive an incorrect ASN value, which prevents synchronisation with the typical network, while in the timeslot template attack, the malicious node can make the legitimate nodes calculate the error clock offset. The authors propose an enhanced secure time synchronisation protocol to defend against these attacks, which include Sec_ASN and TOF algorithm. The Sec_ASN and threshold filter (TOF) algorithms are used to defend against ASN attack and timeslot template attacks, respectively. Finally, the authors run a thorough set of simulations to assess the effectiveness of the proposed attacks as well as the proposed countermeasure. The results show that the attacks can significantly destroy the time synchronisation protocol, but can be successfully defended using the proposed mechanisms.

Time synchronization is very important in the IEEE802.15.4e network which aim to industrial automation applications. It enabled high end-to-end reliability and low power wireless networking. If an adversary launches time synchronization attacks to the IEEE802.15.4e networks, the whole network communications will be paralyzed. In this paper, we present two types of attacks: 1) ASN and 2) time synchronization tree attack. In ASN attack the legitimate nodes may get an incorrect ASN value and thus can't synchronize to the normal network, while in time synchronization tree attack, the attacker can damage the structure of time synchronization tree by faking DIO packets. We propose some countermeasures which include intrusion detection algorithms, Encryption and Authentication methods to defend against these attacks. Finally, we perform time synchronization tree attack experiments. The experiment results show that the proposed mechanisms can defend against the attack.

In recent literatures, WiFi signals have been widely used to "sense" people's locations and activities. Researchers have exploited the characteristics of wireless signals to "hear" people's talk and "see" keystrokes by human users. Inspired by the excellent work of relevant scholars, we turn to explore the field of human-computer interaction using finger-grained gestures under WiFi environment. In this paper, we present Wi-Finger - the first solution using ubiquitous wireless signals to achieve number text input in WiFi devices. We implement a prototype of WiFinger on a commercial Wi-Fi infrastructure. Our scheme is based on the key intuition that while performing a certain gesture, the fingers of a user move in a unique formation and direction and thus generate a unique pattern in the time series of Channel State Information (CSI) values. WiFinger is deigned to recognize a set of finger-grained gestures, which are further used to realize continuous text input in off-the-shelf WiFi devices. As the results show, WiFinger achieves up to 90.4% average classification accuracy for recognizing 9 digits finger-grained gestures from American Sign Language (ASL), and its average accuracy for single individual number text input in desktop reaches 82.67% within 90 digits.

In a number of networking applications, preserving the privacy of user-related data in data aggregation schemes is a fundamental issue. As a fact, many privacy-preserving protocols can be guaranteed with security against individual attacks, but they may be threatened by collusion between participants. Therefore, security analysis, especially for collusion attack analysis, plays an essential role in privacy-preserving data aggregation protocols. There do exist a few collusion attack schemes on data aggregation protocols, but none study the internal security mechanism of these protocols. In this paper, to our best knowledge, we are the first to propose a new kind of collusion attack analysis tool, which is named CAE (Collusion Attack Emulator). We employ it to check and judge the security of several existing privacy-preserving data aggregation schemes. We first show that for an aggregation scheme which has been known to be vulnerable under collusion attack, we can use CAE to explain why it is insecure. Then we demonstrate the blind detection function of CAE, i.e., we do not know whether an aggregation protocol is secure beforehand, and employ CAE to check its security and (if the protocol cannot pass the CAE test and thus to be insecure) to find its loophole.

Spatial Crowdsourcing (SC) nowadays has become a popular research topic studying how to outsource a set of spatial-temporal tasks to workers at specific locations. However, there exists a significant security concern: existing location privacy techniques are not applicable to SC. In this paper, we focus on protecting the worker location privacy against the semi-honest adversaries model while preserving the functionality of SC system. By introducing a semi-honest third party and using additive homomorphic encryption, we present a secure task assignment protocol for SC. More specifically, we propose an efficient protocol to securely compute the worker travel cost and select minimum cost worker in the encrypted domain, which reveals nothing about location privacy. We theoretically analyze that our protocol is secure as all encrypted private data are computationally indistinguishable. Extensive experimental results on real-world and synthetic datasets show that the proposed protocol can protect worker location privacy while keeping high task assignment rate.

Histogram estimation is one of the fundamental tasks in crowdsourcing data aggregation. Since contributing data reveal more or less information about individuals' identifications and activities, participants need to preserve privacy of data according to their own levels of privacy concern. However, most of the existing work only aggregates data with an identical privacy level. In this paper, we propose an aggregation scheme for histogram estimation, wherein participants can publish their data at personalized differential-privacy levels. The aggregator also benefits from potential wider engagement or more honest data. Specially, since privacy levels under personalized privacy policy are sensitive information for participants, our scheme permits participants to keep their privacy levels secret even from the aggregator. We also show how to further optimize the estimation accuracy under given privacy levels by choosing specific randomization strategies.

The application-layer covert channels have been extensively studied in recent years. Information-hiding in ubiquitous application packets can significantly improve the capacity of covert channels. However, the undetectability is still a knotty problem, because the existing covert channels are all frustrated by proper detection schemes. In this paper, we propose LiHB, a behavior-based covert channel in HTTP. When a client is browsing a website and downloading webpage objects, we can reveal some fluctuation behaviors that the distribution relationship between the ports opening and HTTP requests are flexible. Based on combinatorial nature of distributing N HTTP requests over M HTTP flows, such fluctuation can be exploited by LiHB channel to encode covert messages, which can obtain high stealthiness. Besides, LiHB achieves a considerable and controllable capacity by setting the number of webpage objects and HTTP flows. Compared with existing techniques, LiHB is the first covert channel implemented based on the unsuspicious behavior of browsers, the most important application-layer software. Because most HTTP proxies are using NAPT techniques, LiHB can also operate well even when a proxy is equipped, which poses a serious threat to individual privacy. Experimental results show that LiHB covert channel achieves a good capacity, reliability and high undetectability.

The popularity of mobile devices has far expanded the application scenarios of spatial crowdsensing, due to its ability to provide fine-grained multi dimensional sensor readings associated with location information. Privacy is one of the fundamental issues in crowdsensing, as these location-based sensor readings may reveal identities or activities of participants. In this paper, we adopts the state-of-art location privacy definition geo-indistinguishability, provide an efficient and effective privacy preserving histogram aggregation mechanism BFMM (Bit Flipping Matrix Mechanism) for fine-grained multi dimensional location-based data. Theoretical analyses and experimental results demonstrate the efficiency and effectiveness of our approach for fine-grained multidimensional location-based data. Specifically, the aggregation accuracy of our approach averagely outperforms existing methods by a factor of number of buckets in the histogram.

Unlike traditional auction schemes that do not take security into account, a good secure auction scheme first has to satisfy the following two properties: 1) correctness: the auction result should be the same as the result using traditional correct schemes; 2) security: during the auction process, the final result is the only information revealed to the participants. Furthermore, the secure auction scheme should be efficient enough so that the final result can be determined within a reasonable time. Existing works mainly deal with single-sided spectrum auction, and are not totally secure though claimed to be secure. For example, in [2], the auctioneer can easily know the sums of bids for all the possible allocations, and in [3], the auctioneer can obtain the bids of all buyer groups and their ranking order in the auction. This kind of information is sensitive and should be kept secret. In a very timely recent study [4], the authors propose PS-TRUST, a solution for secure double spectrum auction based on TRUST [5]. To our best knowledge, this is the first work that achieves both correctness and security for secure spectrum auction. Unfortunately, the efficiency of this work is not satisfactory.

Performing efficient data aggregation while keeping the property of privacy preservation of user-related data is of high concern. Extensive research has been conducted to address this problem in multiple areas. As a fact, the security of a number of privacy-preserving protocols are threatened by collusion between participants. Therefore, security analysis plays a fundamental role in privacy-preserving data aggregation protocols. In this paper, we present a new kind of collusion attack strategy called Hamburger Attack. It is of logical simplicity, but has the advantage of being effective and efficient. We employ it to check the security of several existing privacy-preserving data aggregation schemes. We show that under hamburger attack, some prior privacy-preserving data aggregation protocols will disclose part, even all, of the private data that they intended to protect. On the other hand, the hamburger attack is beneficial to designing new privacy-preserving data aggregation schemes. It can assist them in avoiding this kind of collusion attack.

In this paper, we propose differentially private protocols for Naive Bayes classification over distributed data. Compared with existing works, the privacy and security models in the proposed protocols are stronger: firstly, both the miner and parties can be arbitrarily malicious and can collude with each other to violate the remaining honest parties privacy; secondly, all communication channels between them can be assumed to be insecure. Specifically, we build a guarantee of differential privacy into the cryptographic construction so that the proposed protocols can tolerate collusions and resist eavesdropping attacks which are caused by insecure communication channels. Additionally, the proposed protocols can be implemented at lower computation and communication costs, and some extensions to our protocols (e.g. supporting parties dynamic joins or leaves) are also proposed in this paper. Both theoretical analysis and simulation results show that the proposed privacy-preserving protocols for Naive Bayes have strong security and better classification performance than the standard one.

A cyclic mobile social network (MSN) is a new type of delay tolerant network, in which mobile users periodically move around, and contact each other through their carried short-distance communication devices. In this paper, we introduce utility-based routing into cyclic MSNs, and propose a deadline-sensitive utility-based routing model. If a message is successfully delivered to its destination before a deadline, its source will receive a positive benefit as the reward. Otherwise, the source receives zero benefit. Also, each message delivery incurs a forwarding cost, no matter whether it succeeds or fails. The utility of a message delivery is defined as the benefit minus the forwarding cost. Under this model, we propose a deadline-sensitive opportunistic utility-based single-copy routing algorithm, DOUR. Each node first determines an optimal forwarding sequence, which is composed of a series of forwarding opportunities, in a distributed and greedy manner. Then, it forwards messages via these forwarding opportunities. Theoretical analysis and extensive simulations prove that DOUR can achieve the optimal utility for each message delivery. Moreover, we extend our algorithm to the case of multi-copy routing, and show that our proposed algorithms can inherently make a good tradeoff among the benefit, delay, and cost for each message delivery.

Abstract Covert channels are malicious conversations disguised in legitimate network communications, allowing information leak to the unauthorized or unknown receiver. Various network steganographic schemes that modify the header fields of transmission control protocol/Internet protocol (TCP/IP) have been proposed in recent years. People before conducted detection research based on the surface content of the header field and did not take into account the differences between the behavior characters of covert channels and the inherent behavior regularities of the header fields. Up to date, there is little comprehensive research on the steganalysis against the storage covert channels. In this paper, we focus on the detection of storage covert channels and introduce a novel comprehensive detection method based on the protocol behaviors. The protocol behavior characters are utilized to evaluate the regularities or correlations of header fields between adjacent packets according to the conventional use. First, the behavior features of the header fields in TCP/IP are extracted; a support vector machine is then applied to the behavior feature sets for discovering the existence of covert channels. Some recognized covert channel tools are detected in our detection experiment. Experimental results and discussion show that our detection method is of effectiveness. Copyright © 2014 John Wiley & Sons, Ltd.

Truthful spectrum auctions have been extensively studied in recent years. Truthfulness makes bidders bid their true valuations, simplifying greatly the analysis of auctions. However, revealing one's true valuation causes severe privacy disclosure to the auctioneer and other bidders. To make things worse, previous work on secure spectrum auctions does not provide adequate security. In this paper, based on TRUST, we propose PS-TRUST, a provably secure solution for truthful double spectrum auctions. Besides maintaining the properties of truthfulness and special spectrum reuse of TRUST, PS-TRUST achieves provable security against semi-honest adversaries in the sense of cryptography. Specifically, PS-TRUST reveals nothing about the bids to anyone in the auction, except the auction result. To the best of our knowledge, PS-TRUST is the first provably secure solution for spectrum auctions. Furthermore, experimental results show that the computation and communication overhead of PS-TRUST is modest, and its practical applications are feasible.

Certificateless cryptography is a new type of public key cryptography, which removes the certificate management problem in traditional public key cryptography and the key escrow problem in identity-based public key cryptography. Multi-proxy signature is an extension of proxy signature, which allows an original signer authorizing a group of proxy signers and only the cooperation of all proxy signers in the group can create valid proxy signatures on behalf of the original signer. Recently, Jin and Wen combined certificateless cryptography with multi-proxy signature, and proposed a model as well as a concrete scheme of certificateless multi-proxy signature. They claimed that their scheme is provably secure in their security model. Unfortunately, in this paper by giving two attacks, we will show that their certificateless multi-proxy signature scheme can be broken. The first attack indicates their security model is flawed and the second attack indicates their certificateless multi-proxy signature scheme is insecure. Possible improvements are also suggested to prevent these attacks.

In this work, we study spectrum auction problem where each spectrum usage request has spatial, temporal, and spectral features. After receiving bid requests from secondary users, and possibly reserve price from primary users, our goal is to design truthful mechanisms that will either optimize the social efficiency or optimize the revenue of the primary user. As computing an optimal conflict-free spectrum allocation is an NP-hard problem, in this work, we design near optimal spectrum allocation mechanisms separately based on the techniques: derandomized allocation from integer programming formulation, and its linear programming (LP) relaxation. We theoretically prove that 1) our derandomized allocation methods are monotone, thus, implying truthful auction mechanisms; 2) our derandomized allocation methods can achieve a social efficiency or a revenue that is at least $1-\frac{1}{e}$ times of the optimal respectively; Our extensive simulation results corroborate our theoretical analysis.

In order to save energy of sensors in the process of gathering data and transmitting information, Compressive Sensing (CS), as a novel and effective signal transform technology, has been used gradually in Wireless Sensor Networks (WSNs). In traditional usages of CS techniques in the previous literatures, the sparsities of the signals has to be known beforehand, which is much more importance for their recover results. However, it is difficult to realize precisely the structures of the signals actually in WSNs. Therefore, it is important to further exploit reasonable practicality availability in actual applications. In order to reduce energy of gathering and transmitting of sensors, this paper presents a model of optimized CS based on local regional data and design two corresponding algorithms, which could reconstruct the signals accurately and stably even if their sparsities could not be known in advance. Most important, our algorithms just need once extra transmission by sensors In the paper, we present two reasonable assumptions and then propose spatial-temporal correlation model for optimizing measure matrix of CS. Furthermore, two algorithms are designed in two kinds of situations that data satisfy random distribution or Gauss distribution, which is common in actual applications. According to experiments in the cases of both real data based on actual environments and two kinds of signals above based on simulation environments, our algorithm has been proved to be valuable for actual applications. Especially, when the amount of the sampling is only 15 with the dimension of the data is 256 and the sparsity is unknown, the relative error rate could be less than 6% in actual environments and 3.5% in simulation environments.

Scalar product protocol and privacy preserving add to multiply protocol (PPAtMP) are two significant basic secure multiparty computation protocols. In this paper, we claim that the two protocols are equivalent to each other and we can achieve one based on the other with the same communication and computation complexity. Then, we propose Secure Two-party Mean Protocol, Secure Shared x ln x Protocol and Secure Shared Generic Polynomial Protocol based on scalar product protocol and PPAtMP. Additionally, we analyze the correctness, security, communication overheads and computation complexity of each protocol proposed in this paper.

This demonstration presents a mobile surveillance system that is developed at the University of Science and Technology of China and undergoing a technology transition. The goal of this project is to develop a low-cost, promptly-deployable, mobility manageable, location traceable, self-organizing wireless communication and mobile surveillance system, for real-time video surveillance and on-site guard for public security purposes, e.g., public security against terrorism in large-scale gatherings and events.

In this paper, a novel statistical algorithm for linguistic steganography detection, which takes advantage of distribution of words in the text segment detected, is presented. Linguistic steganography is the art of using written natural language to hide the very presence of secret messages. Using the text data, which is the foundational media in Internet communications, as its carrier, linguistic steganography plays an important part in Information Hiding (IH) area. The previous work was mainly focused on linguistic steganography and there were few researches on linguistic steganalisys. We attempt to do something to help to fix this gap. In our experiment of detecting the three different linguistic steganography methods: NICETEXT, TEXTO and Markov-chain-Based, the total accuracies on discovering stego-text segments and normal text segments are found to be 87.39% 95.51%, 98.50%, 99.15% and 99.57% respectively when the segment size is 5 kB, WkB, 20 kB, 30 kB and 40 kB. Our research shows that the linguistic steganalysis based on distribution of words is promising.

Word shift is a fundamental format based text steganography. It embeds secret information in text by shifting words slightly. Compared with study on steganography, research on its steganalysis is still in its infancy. In this paper, we present a blind steganalysis method to detect word shift in PDF document. Our method is to find features sensitive to word shift and use classifier to learn and remember feature differences between natural document and stego one. In order to design sensitive features, we propose two concepts "neighbor difference" and "environment equal", which reveal the spaces' statistical property. Then, we divided the PDF document into two types to make our method work efficiently. At last, we design a series of experiments to demonstrate performance of our method. The detection accuracy of our method can be up to 93.3%. Our initial results shows that our proposed concepts are very useful in text steganalysis and offer help for other related works.