Backdoor attacks pose a serious threat to the security of large language models (LLMs), causing them to exhibit anomalous behavior under specific trigger conditions. The design of backdoor triggers has evolved from fixed triggers to dynamic or implicit triggers. This increased flexibility in trigger design makes it challenging for defenders to accurately identify their specific forms. Most existing backdoor defense methods are limited to specific types of triggers or rely on an additional clean model for support. To address this issue, we propose a backdoor detection method based on attention similarity, enabling backdoor detection without prior knowledge of the trigger. Our study reveals that models subjected to backdoor attacks exhibit unusually high similarity among attention heads when exposed to triggers. Based on this observation, we propose an attention safety alignment approach combined with head-wise fine-tuning to rectify potentially contaminated attention heads, thereby effectively mitigating the impact of backdoor attacks. Extensive experimental results demonstrate that our method significantly reduces the success rate of backdoor attacks while preserving the model’s performance on downstream tasks.

Retrieval-Augmented Generation (RAG) techniques have emerged as a promising direction to merge the non-parametric knowledge into Large Language Models (LLMs), thereby alleviating factual errors, hallucinations and outdated knowledge. Existing RAG methods, which append multiple retrieved documents or passages to the input of LLMs, will inevitably increase the context length, resulting in not only significant computational overhead and inference latency, but also performance degradation. Although reranking or compression modules have been introduced to address these challenges, they overlook the contextual preferences of the generative LLMs itself and may inadvertently discard information that is crucial for generation accuracy. To this end, we introduce InnerRAG, which incentivizes RAG via Inner Adaptive Context Selection. InnerRAG is a novel paradigm that empowers LLMs to autonomously select relevant context during generation. Our proposed InnerRAG endows the model to accurately identify the documents that are most helpful for generation from long contexts. By endowing the model with this capability, InnerRAG facilitates more effective exploitation of external knowledge without being misled by disturbed information, leading to substantial improvements in generation quality while maintaining computational efficiency. Extensive experiments across multiple benchmarks and human evaluations demonstrate that our method consistently outperforms state-of-the-art RAG baselines. Moreover, our framework is orthogonal and complementary to in-context RAG approaches, offering further performance improvements when combined.

This paper investigates how to leverage emerging non-volatile memory (NVM) to enhance the performance of Log-Structure Merge (LSM) tree based key-value (KV) stores. We propose KVFG-DB, which efficiently integrates fine-block granularity and single-NVM-level compaction, to deliver high write and read performance with minimal write amplification and reduced write stalls. KVFG-DB leverages a streamlined SSTable layout called CSSTable to manage data blocks (each containing ordered KV pairs) and their indexes (i.e., the minimal and maximal keys of every block), optimizing both storage costs and compaction performance. It organizes the LSM-tree data as CSSTables into a single level on NVM, with the left area serving as a buffer to receive flushed data with substantially greater capacity, and the right area storing compacted data in a global order among CSSTables. A fine-grained compaction is then performed under various conditions to select the most relevant data blocks with intersecting keys from CSSTables in both areas, facilitating byte-addressable, fast parallel execution across multiple threads. As a result, KVFG-DB adaptively compacts data and quickly moves them from the left area to the right area to enhance performance efficiency, significantly reducing write amplification and further mitigating write stalls. Our extensive experimental studies demonstrate that KVFG-DB achieves 1.2× and 2× lower write amplification, compared with state-of-the-art KV stores MioDB and SLM-DB. Accordingly, KVFG-DB shows a 1.1× and 7.1× improvement in random write performance compared to them, with tail latency reduced by 1.1× and 7×, respectively.

Redactable blockchains preserve the integrity of hash links while enabling authorized redactions to comply with regulatory requirements. However, existing permissioned solutions suffer from three severe issues. First, fine-grained privilege control incurs significant storage overhead, especially in the case of single-use authorization. Second, the reliance on bilinear pairings in chameleon hash leads to significant performance degradation when handling large-scale redaction requests. Finally, multiple incorporated components often unconsciously introduce centralized entities, undermining the decentralized nature. In this paper, we propose MithrilRB, a resource-efficient and decentralized redactable blockchain with single-use authorization. Specifically, we introduce a privilege control mechanism with our proposed multi-authority attribute-based signature (MA-ABS) and the threshold BLS signature, achieving fine-grained single-use authorization and direct user revocation without extra ciphertext storage. We also design a pairing-free non-interactive threshold chameleon hash (PNITCH), which enhances efficiency and is better suited for large-scale redaction requests. Moreover, MithrilRB eliminates centralized trust points that hold secret information, ensuring fully decentralization-compatible functional integration in redactable blockchains. Finally, we implement MithrilRB, and the experimental results demonstrate that MithrilRB significantly outperforms existing solutions in both computational efficiency and storage requirements.

As image data outsourcing to mobile cloud grows, data privacy has become a major concern. Privacy-preserving image retrieval aims to search over encrypted data without requiring decryption. However, existing schemes face three critical challenges: struggle to balance accuracy, efficiency, and security; limited scalability for large-scale image retrieval in multi-user settings; and vulnerability to security threats arising from user permission changes or key compromises. In this paper, we propose ELSEIR, a novel framework for accurate, efficient, and privacy-preserving image retrieval. ELSEIR leverages a deep hashing model to extract image feature vectors and designs an irreversible random hash code generation module that combines secure permutation keys with two differential privacy methods for privacy protection. To enable accurate searches in multi-user settings, ELSEIR introduces a key conversion protocol that allows the cloud to unify ciphertexts encrypted under different user keys via corresponding switch keys. Furthermore, we extend the framework to ABE-ELSEIR, which supports immediate and efficient user revocation. We further provide formal security proofs demonstrating that the proposed frameworks are resilient against known-plaintext and key collusion attacks. Extensive experiments on real-world datasets show that our scheme achieves accuracy comparable to the unprotected baseline, while surpassing existing approaches in both retrieval accuracy and efficiency.

Backdoor attacks threaten the reliability of NLP models by embedding hidden behaviors during training, which are activated by specific inputs at inference time. Traditional backdoor triggers often rely on explicit content alterations-such as token insertion or stylistic modification-which may compromise semantic coherence and be easily detected.In this work, we propose a novel backdoor attack strategy that leverages the linguistic properties of code-mixing(a language form that combines elements from two or more languages) as implicit triggers. Drawing inspiration from natural code-mixing communication, we design three types of linguistically grounded triggers: inter-word mixing, intra-sentential mixing, and inter-sentential mixing. These forms reflect realistic language usage patterns in bilingual communities, enhancing the stealthiness of the attack. The experiment results show that existing NLP models perform poorly when faced with backdoor attacks based on code-mixing triggers. We are the first to focus on code-mixing as a trigger for text backdoor attacks. We hope this research raises awareness of the vulnerability of models during training when faced with code-mixing.

Retrieval-Augmented Image Captioning enhances the model's understanding of real-world images by retrieving external knowledge. Existing methods mainly use original captions or isolated entities related to the query image to help generate captions. However, these methods make the model either imitate the caption style or fail to capture the relationship between entities, resulting in a lack of diversity or inaccuracy in the generated captions. To address these issues, we propose SEAR, a novel framework that utilizes external Synthesized Entity-Aware knowledge Representations to improve captioning performance. Specifically, SEAR clusters images based on scene-level and entity-level features, and synthesizes each clustered images into representative images as retrieval indexes, and simultaneously utilizes a large model to extract and supplement structured knowledge graphs from the corresponding cluster captions. Furthermore, we design a knowledge-graph pruner to prune the knowledge graph by retaining the most relevant subgraphs to the query image. By undertaking these steps in an integrated manner, SEAR enables the model to acquire non-redundant and structured information for generating captions and avoid data-related privacy issues. Extensive experiments on MSCOCO, Flickr30k, and NoCaps demonstrate the effectiveness of our method both in-domain and out-of-domain, outperforming existing lightweight RAIC methods and remaining competitive with heavyweight models.

The rapid development and widespread adoption of cloud computing have made privacy-preserving data retrieval in the cloud a hot topic in privacy computing research. While numerous schemes have been proposed for privacy-preserving text-to-text and image-to-image retrieval, there is a lack of research on cross-modal retrieval with privacy protection in the cloud, leaving ample room for enhancing the security and efficiency of existing schemes. To address these challenges, this paper proposes a scheme for privacy-preserving cross-modal retrieval. The proposed scheme leverages a cross-modal pretrained model to extract features from both text and images, which are then mapped into hash buckets using locality-sensitive hashing (LSH), thereby enhancing retrieval efficiency. Additionally, a data structure is employed to generate secure indexes for these hash buckets via symmetric searchable encryption (SSE). To further improve retrieval accuracy, a secure k-nearest neighbor (kNN) algorithm is applied for second-round ranking of the retrieval results. Analysis and extensive experiments on widely-used real-world datasets have demonstrated the scheme's effectiveness in preserving privacy while maintaining efficiency and feasibility.

Federated Learning (FL) addresses data privacy and security in distributed machine learning. However, it performs poorly in real-world applications due to non-IID client data. Fortunately, recent advancements in data distillation offer a solution to generate a compressed and privacy-preserving distilled dataset that approximates the original dataset. Nonetheless, the current data distillation for FL usually indiscriminately distills information from all the samples through multiple communication rounds, which will inevitably generate redundant information and reduce the convergence speed. In this paper, we propose a novel local active data distillation method, which enables the global model to actively distill data that are beneficial for its training from each local dataset. Subsequently, we design a selective knowledge distillation to refine the global model by aligning it with an accurate expert model. Experimental results on multiple datasets have demonstrated the effectiveness of our method compared with the state-of-the-art methods.

Given a text query, partially relevant video retrieval (PRVR) aims to retrieve untrimmed videos containing relevant moments, wherein event modeling is crucial for partitioning the video into smaller temporal events that partially correspond to the text. Previous methods typically segment videos into a fixed number of equal-length clips, resulting in ambiguous event boundaries. Additionally, they rely on mean pooling to compute event representations, inevitably introducing undesired misalignment. To address these, we propose an Uneven Event Modeling (UEM) framework for PRVR. We first introduce the Progressive-Grouped Video Segmentation (PGVS) module, to iteratively formulate events in light of both temporal dependencies and semantic similarity between consecutive frames, enabling clear event boundaries. Furthermore, we also propose the Context-Aware Event Refinement (CAER) module to refine the event representation conditioned the text’s cross-attention. This enables event representations to focus on the most relevant frames for a given text, facilitating more precise text-video alignment. Extensive experiments demonstrate that our method achieves state-of-the-art performance on two PRVR benchmarks. Code is available at https://github.com/Sasa77777779/UEM.git.

Multimodal hashing projects multimodal data into compact binary codes, enabling rapid and storage-efficient retrieval of large-scale multimedia content. In practical scenarios, the issue of missing modality frequently arises when dealing with multimodal data. Existing incomplete multimodal hashing techniques directly recover missing modalities by neural networks, resulting in a disjointed representation space between the recovered and true data. In this paper, we present a novel recovery paradigm, namely Prototype-based Modality Completion Hashing (PMCH). Instead of directly synthesizing it from available modalities, PMCH adaptively aggregates associated within-modality prototypes to recover missing modality data. Specifically, PMCH introduces an within-modality prototype learning module to optimize representative prototypes for each modality. These prototypes act as recovery anchors and reside within the same representation space as their corresponding modality data. Subsequently, PMCH adaptively aggregates the associated within-modality prototypes with coefficients derived from the modality-specific Weight-Net. By utilizing prototypes from the same modality, the semantic disparity between the reconstructed and authentic data can be substantially diminished. Extensive experiments on three widely used benchmark datasets demonstrate that PMCH can effectively recover the missing modality, and attain state-of-the-art performance in both complete and incomplete multimodal retrieval scenarios. Code is available at https://github.com/Sasa77777779/PMCH.git.

Efficiently managing data transmission across unreliable communication channels for diverse sources has attracted much attention due to its great practicability in the Internet of Things systems. Despite its significance in real-time wireless systems, ensuring stringent freshness requirements for each information source remains an understudied challenge, especially in scenarios demanding heterogeneous quality-of-service guarantees. In this paper, we study a scheduling problem of maximizing the accumulated information subject to different Age of Information (AoI) requirements for heterogeneous information sources. To that end, we first present a global optimal transmission scheduling policy when the source statistics are known a priori. Then, as this information is unknown, we formulate the problem as an AoI-constrained Multi-Armed bandit and propose an efficient learning algorithm, named O-SRS. Furthermore, we theoretically show that O-SRS achieves$O(\sqrt{T \log T})$regret while meeting the AoI requirement of each source. Finally, comprehensive simulations are conducted to demonstrate our theoretical results.

Unsupervised cross-domain image retrieval (UCDIR) aims to retrieve images across different domains without the guidance of labels. However, existing UCDIR methods assume that data can be shared across domains in plaintext, which is often impractical due to strict data privacy protection policies. In this paper, we propose ShieldIR, a novel privacy-preserving unsupervised cross-domain image retrieval framework that enhances the retrieval performance across two domains while safeguarding data privacy. ShieldIR unifies intra-domain and cross-domain representation learning through a Dual Protection Transformation (DPT) module, which introduces a structured feature space via orthogonal projection and ensures data privacy by adding calibrated differential privacy noise. This transformation allows ShieldIR to preserve semantic structure while formally protecting private data. For intra-domain representation learning, ShieldIR enhances discriminability by using DPT to map prototypes into an independent feature space and subsequently aligning the resulting dual-protected prototypes with instance-level features. For cross-domain alignment, ShieldIR maps intra-domain features and cross-domain prototypes into a shared structured space using DPT, achieving semantic alignment under privacy constraints. Extensive experiments on real-world datasets demonstrate that our ShieldIR outperforms state-of-the-art methods while effectively protecting data privacy.

Retrieval-augmented generation (RAG) paradigms can integrate external knowledge to enhance and validate the output of Large Language Models (LLMs) thereby mitigating generative hallucinations and broadening the model's knowledge scope. Despite advancements, existing RAG methods still suffer from uncertainty of prediction during the multi-round retrieval-generation process, and a lack of the ability to balance the adequacy and redundancy of retrieved information. To address these challenges, we propose CIRAG, an approach that combines the RAG process with collective intelligence. Inspired by the crowd of wisdom, CIRAG simulates individual independent decision-making and information aggregation within a crowd. Specifically, CIRAG first enhances retrieval diversity by expanding queries based on extracted entities, then combines frequency-based and semantic-based reranking to form a multi granularity fusion reranking thereby assessing better relevance, and integrate multiple information sources for accurate content generation. By undertaking these steps in an integrated manner, CIRAG enables the model to acquire comprehensive and non-redundant information for generating responses. We conduct extensive experiments with HotPotQA and 2WikiMultihopQA datasets, popular benchmark for retrieval-based, multi-step question-answering. Experimental results show that our approach surpasses existing advanced RAG framework while providing high portability in query expansion as well as strong comprehensiveness exhibited in the collective intelligence.

In recent years, the study on defending deep hashing models against adversarial attacks has garnered increasing attention. Among them, adversarial training is an effective method to train robust deep hashing models. Existing adversarial training methods for deep hashing simultaneously optimize original deep hashing loss and proposed adversarial training loss to train a robust model. However, we argue that directly using the original deep hashing loss will guide the model to learn excessive non-robust patterns from clean examples when extracting discriminative semantic information, thereby limiting model robustness. To tackle this, we propose a novel Clean model Representation Distillation based Adversarial Training (CRDAT) method, which enables the robust model to learn both discriminative semantic information and robust patterns by separating these two losses into two stages, i.e., standard training stage of a clean teacher model and adversarial training stage of a robust student model. Specifically, we propose a novel representation distillation based adversarial training loss, which distills the representations of the teacher model on clean examples at both the hash code level and feature level to guide the student model's learning on adversarial examples. Extensive experiments on multiple datasets and deep hashing methods demonstrate that our CRDAT method can greatly improve model robustness and achieve state-of-the-art defense performance.

Secure cloud-edge data sharing has been researched recently to provide high quality on-demand data service. Attribute-based encryption (ABE) is a promising solution that achieves data confidentiality and flexible access control simultaneously. But three major issues remain when adapting ABE in cloud-edge, namely reliable user revocation, high performance on devices, and trust issues of public cloud. First, existing direct user revocation mechanisms focus on preventing a revoked user from decrypting header ciphertexts even when key exposure occurs, but ignore the payload security. Second, how to conveniently apply deployment on diverse platforms and run programs on resource-constrained devices with high efficiency is a challenge. Finally, no universal guarantee of cloud computation and management tasks, thus lazy or malicious cloud may not follow the protocol and perform improper actions on purpose. In this work, we propose a Hardware-Assisted Hybrid Fully Outsourced Revocable Attribute-Based Proxy Re-Encryption (H²O-RABPRE) scheme that supports reliable user revocation for full data traffic and hardware-assisted fully outsourced computation. Moreover, we design a hardware-assisted data-sharing framework with rapid deployment for cloud-edge, which integrates the developed SGX-MCL to protect outsourced tasks executed by cloud/edge devices against malicious behaviors and utilizes the enhanced WebAssembly runtime, WasmCrypto, a unified deployment approach for IoT devices with near-native performance. We implement the scheme on an SGX cloud server, a laptop, a Raspberry Pi, and an ESP32 board, and the results indicate that the proposed scheme is practical.

Searchable Symmetric Encryption (SSE) enables clients to make confidential queries over encrypted data while revealing some formally-defined leakage profiles. Despite the promising performance and application prospects of SSE, the recent leakage-abuse attacks show that a passive adversary can recover queries by exploiting patterns about data disclosed from leakage profiles. Among those attacks, the size pattern is a frequently exploited leakage. Although several countermeasures have been proposed, they can provide neither sufficient protection to mitigate size pattern leakage, nor sufficient scalability for large-scale databases. To address those challenges, we present an SGX-based size-pattern mitigation SSE schemeSMSSEwith two tailored response padding approaches and an I/O efficient disk-based index construction. In addition, we evaluate the size pattern leakage after padding through conditional entropy and differential privacy. Furthermore, we demonstrate the scalability robustness ofSMSSEon different databases by theoretically deducing the approximate boundary of index reading efficiency under a reasonable query distribution. Experiment results on representative real-world datasets show thatSMSSEcan provide high utility and strong protection against newly size pattern-based leakage-abuse attacks.

Deep incremental hashing has become a subject of considerable interest due to its capability to learn hash codes in an incremental manner, eliminating the need to generate codes for classes that have already been learned. However, accommodating more classes requires longer hash codes, and regenerating database codes becomes inevitable when code expansion is required. In this paper, we present a unified deep hash framework that can simultaneously learn new classes and increase hash code capacity. Specifically, we design a triple-channel asymmetric framework to optimize a new CNN model with a target code length and a code projection matrix. This enables us to directly generate hash codes for new images, and efficiently generate expanded hash codes for original database images from the old ones with the learned projection matrix. Meanwhile, we propose a pairwise-label-based incremental similarity-preserving loss to optimize the new CNN model, which can incrementally preserve new similarities while maintaining the old ones. Additionally, we design a double-end quantization loss to reduce the quantization error from new and original query images. As a result, our method efficiently embeds both new and original similarities into the expanded hash codes, while keeping the original database codes unchanged. We conduct extensive experiments on three widely-used image retrieval benchmarks, demonstrating that our method can significantly reduce the time required to expand existing database codes, while maintaining state-of-the-art retrieval performance.

Traditional in-memory graph systems often suffer from scalability due to the limited capacity and volatility of DRAM. Emerging non-volatile memory (NVM) provides an opportunity to achieve highly scalable and high-performance graph stores for its large capacity and persistence characteristics. However, directly deploying current in-memory graph storage systems on NVM would cause significant inefficiencies in NVM access, as their graph organization designed for DRAM may incur higher write amplification, crash inconsistency and costly concurrency control overhead in NVM for write-intensive work-loads. In this paper, we propose FTGraph, a Flexible Tree-based Graph storage system, for both efficient dynamical graph updates and analysis. To achieve this goal, we introduce a novel degree-aware suffix bit tree to effectively manage vertices and edges of the graph, enabling adaptability to real-world power-law degree distributions while significantly reducing NVM writes. Based on it, we adopt two optimization methods, logical vertex ID translation and sequential storage, for vertices with very high degrees within the tree to enhance graph analysis operations. We further integrate 8B NVM atomic writes with optimistic version-based concurrency control through a dual bitmap design to ensure low-overhead, log-free crash consistency and reduce read-writer contention. Experimental results show that FTGraph achieves up to$\mathbf{21.2}\times$higher update performance and up to$\mathbf{85.4}\times$higher analysis performance, compared with state-of-the-art dynamic graph systems implemented on NVMs.

Few-shot relation extraction (FSRE) can alleviate the data scarcity problem in relation extraction. However, FSRE models often suffer a significant decline in performance when adapting to new domains. To overcome this issue, many researchers have focused on domain adaption FSRE (DAFSRE). Nevertheless, existing approaches primarily concentrate on the source domain, which makes it difficult to accurately transfer useful knowledge to the target domain. Additionally, the lack of distinction between relations further restricts the model performance. In this paper, we propose the domain-aware and co-adaptive feature transformation approach to address these issues. Specifically, we introduce a domain-aware transformation module that leverages the target domain distribution features to guide the domain-aware feature transformations. This can enhance the model’s adaptability across domains, leading to improved target domain performance. Furthermore, we design co-adaptive prototypical networks to perform co-adaptive feature transformation through a transformer mechanism. This results in more robust and distinguishable relation prototypes. Experiments on DAFSRE benchmark datasets demonstrate the effectiveness of our method, which outperforms existing models and achieves state-of-the-art performance.

The design of effective online caching policies is an increasingly important problem for content distribution networks, online recommender systems, and edge computing services, etc. Exiting literature usually tackles this problem through the lens of optimistic online learning and aims to achieve sublinear regret. In this paper, we focus on a non-trivial extension of classic online caching problem inspired by operational requirements of real-world systems including switching costs and long-term constraints. To tackle the challenges of switching costs and operational long-term constraints in the online caching, we introduce the Block-structured Follow-the-Regularized-Leader (B-FTRL) caching policy. Our approach incorporates a block structure that divides time into blocks to minimize caching switching costs. The theoretical analysis shows that B-FTRL achieves a utility regret bound of $O\left( {{T^{\frac{{2a - b + 1}}{{1 + a}}}} + {T^{\frac{b}{{1 + a}}}}} \right)$ and switching costs bound of $O\left( {{T^{\frac{1}{{1 + a}}}}} \right)$, where a and b are tunable algorithm parameters. By carefully selecting the values of a and b, we are able to limit the total regret to O(T2/3) while satisfying the operational long-term constraints in expectation. Additionally, we provide high-probability constraint violation bounds of $O\left( {\sqrt T } \right)$. The performance of the proposed algorithm is evaluated with detailed trace-driven numerical tests.

The Application Program Interface (API) security is crucial for data security as it ensures the safety and authority of data exchange between different applications. However, the absence of high-quality datasets significantly impedes the development of API anomaly detection. This paper presents a benchmark dataset and baselines for realistic API anomaly detection involving few-shot and unknown-risk scenarios. The dataset is synthesized using an Iterative data Generation approach with Dual-channel Filtering (IGDF). By leveraging large language models and dual-channel filtering models, we can iteratively generate and filter data, yielding a high-quality dataset. Moreover, we have developed baselines and conducted extensive experiments on the proposed dataset. The results indicate that few-shot and unknown-risk API anomaly detection remains a challenging task and still requires further research. All details and resources are released at https://github.com/yijunL/FUR-API.

federated learning has been introduced into person re-identification (Re-ID) to avoid personal image leakage in traditional centralized training. To address the key issue of statistic heterogeneity in different clients, several optimization methods have been proposed to alleviate the bias of the local models. However, besides statistic heterogeneity, feature heterogeneity (e.g., various angles, different illuminations) in different clients is more challenging in federated Re-ID. In this paper, we propose a meta-knowledge enhanced data augmentation method, where the global cross semantic feature transformations are provided to each client to perform local infinite augmentation to reduce the feature difference in different clients. Specifically, to capture the cross semantic feature transformations in each client, we calculate the covariance matrix of features with the local dataset as the transferable meta-knowledge. Then, this local meta-knowledge is propagated to the server for global aggregation. Subsequently, the aggregated meta-knowledge is sent back to each client for infinite data augmentation. Moreover, since the covariance matrix indicates variations in a client, we design a variation-balanced aggregation to replace the traditional data-size-balanced aggregation. To imitate the more challenging scenario of feature heterogeneity, we focus on the federated-by-camera setting to conduct experiments, where images collected in a camera are regarded as the dataset of a client. Extensive experimental results show that our method outperforms other state-of-the-art methods. Code is available at https://github.com/songchunli1999/MEDA.

Although image-dependent adversarial attacks have been studied, the more challenging image-agnostic adversarial attack for deep hashing remains an unexplored territory. In this paper, we take the first attempt on the more efficient and malicious targeted universal adversarial attack (TUAA) for deep hashing. When previous image-dependent attacks are directly applied to TUAA task, they usually face two main issues. Firstly, existing anchor code generation methods generate anchor code with inferior representative semantic-preserving ability. Secondly, previous methods simply minimize the distance between hash codes and anchor code in Hamming space, which tends to optimize targeted universal adversarial perturbation (TUAP) in a coarse-grained manner. To tackle the above problems, we propose a Semantic-enhanced and Stabilized Targeted Universal Adversarial Attack (SS-TUAA) method. Specifically, we first propose a new Candidate Anchor code Evaluation (CAE) method to generate anchor code with superior semantic-preserving ability. Then, to enhance the ‘dominant role’ and the stability of TUAP, we propose a Feature Consistency Loss (FCL) to align the fine-grained feature representation between TUAP and adversarial examples. Extensive experiments demonstrate the effectiveness of each component within our SS-TUAA method, and our method can achieve the state-of-the-art TUAA performance for deep hashing.

Federated Learning (FL) has emerged as a promising approach to preserve privacy for distributed machine learning, through aggregating gradients calculated from local data of multiple clients. Recent studies show that gradients can be inverted to reconstruct private data retained by local clients in a process called gradient inversion. However, the performance of existing gradient inversion attacks declines as batch size increases. In this work, we propose a simple but effective method to tackle this challenge. Our method utilizes an interesting property between weights, embeddings and their corresponding gradients in fully connected layer, which enables the rapid and accurate recovery of embeddings. And these embeddings benefit the recovery of private data as additional prior knowledge. Extensive experiments demonstrate that our method can perform high-quality recovery of private data.

A critical challenge in federated learning is data heterogeneity, compounded by varying local data distribution, thereby significantly impacting the performance of both local and global models. Prior works struggle to effectively address data heterogeneity but ignore the feature skew. In this paper, we propose a novel method, Federated Learning with Semantic Enhancement (FedSE) to address this challenge. Specifically, we introduce semantic regularization terms and adaptive local aggregation to mitigate the drawback of local knowledge insufficiency and enhance the semantics of representations. Then, based on the neural collapse theory, we initialize a simplex equiangular tight frame structure (ETF) of the classifier and maintain its stability during local training, to achieve alignment in the feature space across different clients. Extensive experiments demonstrate our method achieves SOTA performance on several standard benchmark datasets, effectively alleviating the feature skew.

Person re-identification aims to retrieve the target person from a large-scale dataset, and its performance highly relies on a large, well-annotated training dataset. However, label noise generated by manual mislabeling is usually inevitable in real-world scenarios. An intuitive way to alleviate the effect of label noise is to identify and discard noisy data. Recently, most works recognize noisy samples with their global features, which will omit some noisy samples when they are subtly different from the clean ones. In this paper, we propose to recognize noisy data with local features based on uncertainty estimation. Specifically, for each input image, we randomly erase a part of its features to generate a local feature and propagate it to the softmax layer to obtain a local soft label. Then, we repeat the above operations to obtain multiple local soft labels. Subsequently, we estimate the uncertainty with these multiple local soft labels and utilize them to identify whether this sample is noisy. Finally, we design a noise-aware cross-entropy loss based on the estimated uncertainty to reduce the effect of noisy samples automatically. Experimental results on Market-1501 and CUHK03 datasets show the effectiveness of our proposed model, where at least 4.8% and 1.5% improvements are achieved compared with other methods under 0% and 10% noise settings on Market-1501 datasets. Code is available at https://github.com/songchunli1999/NACE.

Privacy-preserving content-based image retrieval aims to safeguard the security of outsourced private images while maintaining their searchability. However, existing schemes encounter challenges in striking a balance between security, accuracy, and efficiency, as well as difficulties in scaling to large-scale image retrieval in multi-user settings. In this paper, we propose a novel Efficient Large-Scale Encrypted Image Retrieval (ELSEIR) framework for outsourced data sharing. We first utilize a deep hashing model for image feature extraction. Building upon this, we design an irreversible random hash code generation method that incorporates permutation keys for personalized access and integrates differential privacy to further enhance data security. In our multi-user implementation, we distribute the switch keys to the cloud to standardize each key, enabling the accurate search. In addition, we have theoretically proven that our ELSEIR guarantees both outsourced data security and query user privacy. Extensive experiments on real-world datasets demonstrate that our ELSEIR yields comparable accuracy to the unprotected baseline while outperforming existing methods in terms of both retrieval accuracy and efficiency.

Dataset distillation, also known as dataset condensation, offers a possibility for compressing a large-scale dataset into a small-scale one (i.e., distilled dataset) while achieving similar performance during model training. This method effectively tackles the challenges of training efficiency and storage cost posed by the large-scale dataset. Existing dataset distillation methods can be categorized into Optimization-Oriented (OO)-based and Distribution-Matching (DM)-based methods. Since OO-based methods require bi-level optimization to alternately optimize the model and the distilled data, they face challenges due to high computational overhead in practical applications. Thus, DM-based methods have emerged as an alternative by aligning the prototypes of the distilled data to those of the original data. Although efficient, these methods overlook the diversity of the distilled data, which will limit the performance of evaluation tasks. In this paper, we propose a novel Diversified Semantic Distribution Matching (DSDM) approach for dataset distillation. To accurately capture semantic features, we first pre-train models for dataset distillation. Subsequently, we estimate the distribution of each category by calculating its prototype and covariance matrix, where the covariance matrix indicates the direction of semantic feature transformations for each category. Then, in addition to the prototypes, the covariance matrices are also matched to obtain more diversity for the distilled data. However, since the distilled data are optimized by multiple pre-trained models, the training process will fluctuate severely. Therefore, we match the distilled data of the current pre-trained model with the historical integrated prototypes. Experimental results demonstrate that our DSDM achieves state-of-the-art results on both image and speech datasets. Code is available at https://github.com/Li-Hongcheng/DSDM.

Attribute-based encryption (ABE) is a highly promising mechanism for secure fine-grained access control over encrypted data, particularly in cloud storage applications. However, the integration of built-in key escrow and susceptibility to key exfiltration poses a prevalent challenge during the implementation of ABE. In this paper, we present a novel ABE scheme called T-ABE to address the above challenges. Specifically, T-ABE utilizes a Trusted Execution Environment (i.e. Intel SGX) to provide a precise security guarantee for the entire process, from establishing trust between users and ABE services to key generation and management, ensuring that the entire scheme can provide users with secure and reliable ABE key hosting services even when deployed in untrustworthy cloud service providers. Through comprehensive security analysis and experimental demonstration, we have demonstrated the advantages of T-ABE in practical applications. We are confident that this new scheme has the potential to effectively tackle the outsourced key escrow challenges encountered by ABE.

Asymmetric image retrieval methods have drawn much attention due to their effectiveness in resource-constrained scenarios. They try to learn two models in an asymmetric paradigm, i.e., a small model for the query side and a large model for the gallery. However, we empirically find that the mutual training scheme (learning with each other) will inevitably degrade the performance of the large gallery model, due to the negative effects exerted by the small query one. In this paper, we propose Central Similarity Consistency Hashing (CSCH), which simultaneously learns a small query model and a large gallery model in a mutually promoted manner, ensuring both high retrieval accuracy and efficiency on the query side. To achieve this, we first introduce heuristically generated hash centers as the common learning target for both two models. Instead of randomly assigning each hash center to its corresponding category, we introduce the Hungarian algorithm to optimally match each of them by aligning the Hamming similarity of hash centers to the semantic similarity of their classes. Furthermore, we introduce the instance-level consistency loss, which enables the explicit knowledge transfer from the gallery model to the query one, without the sacrifice of gallery performance. Guided by the unified learning of hash centers and the distilled knowledge from gallery model, the query model can be gradually aligned to the Hamming space of the gallery model in a decoupled manner. Extensive experiments demonstrate the superiority of our CSCH method compared with current state-of-the-art deep hashing methods. The open-source code is available at https://github.com/dubanx/CSCH .

Deep incremental hashing methods require a large number of original training samples to preserve old knowledge. However, the old training samples are not always available. This “data-free” setting poses great challenges for learning discriminative codes for new classes (plasticity) and maintaining the code invariance of old ones (stability). On the one hand, the presence of ambiguous data in new-emerging classes, which is highly similar to that in old classes, further aggravates catastrophic forgetting. On the other hand, although well-separated hash codes of new classes can be learned by forcing them towards fixed hash centers, it may significantly change the learned parameters of the old model, leading to severe forgetting on old classes. To alleviate the stability-plasticity dilemma in data-free situations, this paper presents a novel deep incremental hashing method called Data-Free Deep Incremental Hashing (DFIH) from the data to the optimization aspect. We start from the data aspect and propose a data disambiguation module to reveal and discard ambiguous data, especially pixels to alleviate the forgetting issues. Subsequently, we introduce a set of trainable hash proxies during the optimization process. These proxies are optimized adaptively as well as the hash codes, not only guiding the model to learn discriminative hash codes for new classes but also avoiding the dramatic modification of the model’s parameters, thus improving plasticity and maintaining stability. Extensive experiments on six widely-used image retrieval benchmarks and sixteen incremental learning situations show the superiority of DFIH. Ablation analysis further confirms the effectiveness of the components in DFIH. The code of this work is released athttps://github.com/SuQinghang/DFIH.

Network protocol reverse engineering is the basis for many security applications. A common class of protocol reverse engineering methods is based on the analysis of network message traces. After performing message field identification by segmenting messages into multiple fields, a key task is to infer the semantics of the fields. One of the limitations of existing field semantics inference methods is that they usually infer semantics for only a few fields and often require a lot of manual effort. In this paper, we propose an automated field semantics inference method for binary protocol reverse engineering (FSIBP). FSIBP aims to automatically learn semantics inference knowledge from known protocols and use it to infer the semantics of any field of an unknown protocol. To achieve this goal, we design a feature extraction method that can extract features of the field itself and of the field context. We also propose a semantic category aggregation method that abstracts the fine-grained semantics of all fields of known protocols into aggregated semantic categories. Moreover, we make FSIBP infer semantics based on the similarity of fields to semantic categories. The above design enables FSIBP to utilize the semantic knowledge of all fields of known protocols and infer the semantics of any fields of unknown protocols. The whole process of FSIBP does not require any expert knowledge or manual parameter setting. We conduct extensive experiments to demonstrate the effectiveness of FSIBP. Moreover, we find a utility for FSIBP besides field semantics inference, its output can help to detect the mis-segmented fields generated during the message field identification.

We study the caching problem from an online learning point-of-view, i.e., no model assumptions and prior knowledge for the file request sequence. Our goal is to design an efficient online caching policy with minimal regret, i.e., minimizing the total number of cache miss with respect to the best static configuration in hindsight. Previous studies, such as Follow-The-Perturbed-Leader (FTPL) and Follow-The-Regularized-Leader (FTRL) caching policies, have provided some near-optimal results, but their theoretical performance guarantees only valid for the regime wherein all arrival requests could be seen by the cache, which is not the case in some practical scenarios. Hence our work closes this gap by considering the partial-observation regime wherein only requests for currently cached files are seen by the cache, which is more challenging and has not been studied before. We propose an online caching policy integrating the FTPL with a popularity estimation procedure called Geometric Resampling (GR), which is the first no-regret policy in this regime (achieve sublinear regret guarantee). Moreover, in the partial-observation regime, we also consider the caching problem with additional operational requirements of real-world systems, i.e., long-term constraints, and proposed a modified version of FTRL combining with GR to address this challenge setting. The theoretical analysis shows that this caching policy is able to achieve no-regret guarantee while satisfying the operational long-term constraints in expectation. Finally, we conduct numerical experiments to validate the theoretical guarantees of our proposed caching policies.

Signed graphs are prevalent data structures containing both positive and negative links. Recently, the fundamental network analysis task on signed graphs, namely link sign prediction, has received careful attention. Existing methods learn two target node representations independently, and the sign between these two nodes is predicted based on similarity. However, such a paradigm is node-centric that cannot distinguish node pairs with distinct contexts, thus lowering the prediction performance. Learning pair-centric representation is therefore a rewarding way to be aware of differences between pairs. There is no study yet on how to build such an appropriate representation that can effectively infer the sign between the target node pair. In this paper, we provide a new perspective to conduct link sign prediction within the paradigm of subgraph classification and propose a novel Subgraph-based link Sign Prediction (SSP) model. Technically, SSP uses importance-based sampling to extract an informative subgraph around each target node pair. For each subgraph, an innovative node labeling scheme is designed to encode its structural and signed information for representation learning. To further utilize the subgraph representation for imbalanced sign classification, SSP employs self-pruning contrastive learning to gain balanced representations. Extensive experiments on real-world datasets demonstrate that SSP consistently and significantly outperforms all the state-of-the-art baselines.

Video-text retrieval is an emerging stream in both computer vision and natural language processing communities, which aims to find relevant videos given text queries. In this paper, we study the notoriously challenging task, i.e., Unsupervised Domain Adaptation Video-text Retrieval (UDAVR), wherein training and testing data come from different distributions. Previous works merely alleviate the domain shift, which however overlook the pairwise misalignment issue in target domain, i.e., there exist no semantic relationships between target videos and texts. To tackle this, we propose a novel method named Dual Alignment Domain Adaptation (DADA). Specifically, we first introduce the cross-modal semantic embedding to generate discriminative source features in a joint embedding space. Besides, we utilize the video and text domain adaptations to smoothly balance the minimization of the domain shifts. To tackle the pairwise misalignment in target domain, we propose the Dual Alignment Consistency (DAC) to fully exploit the semantic information of both modalities in target domain. The proposed DAC adaptively aligns the video-text pairs which are more likely to be relevant in target domain, enabling that positive pairs are increasing progressively and the noisy ones will potentially be aligned in the later stages. To that end, our method can generate more truly aligned target pairs and ensure the discriminability of target features. Compared with the state-of-the-art methods, DADA achieves 20.18% and 18.61% relative improvements on R@1 under the setting of TGIF→MSR-VTT and TGIF→MSVD respectively, demonstrating the superiority of our method.

Large-scale data from the real-world usually follow a long-tailed distribution (i.e., a few majority classes occupy plentiful training data, while most minority classes have few samples), making the hyperplanes heavily skewed to the minority classes. Traditionally, reweighting is adopted to make the hyperplanes fairly split the feature space, where the weights are designed according to the number of samples. However, we find that the number of samples in a class can not accurately measure the size of its spanned space, especially for the majority class, where the size of its spanned space is usually larger than the samples’ number because of the high diversity. Therefore, weights designed based on the samples’ number will still compress the space of minority classes. In this paper, we reconsider reweighting from a totally new perspective of analyzing the spanned space of each class. We argue that, besides statistical numbers, relations between samples are also significant for sufficiently depicting the spanned space. Consequently, we estimate the size of the spanned space for each category, namely effective area, by detailedly analyzing its samples’ distribution. By treating samples of a class as identically distributed random variables and analyzing their correlations, a simple and non-parametric formula is derived to estimate the effective area. Then, the weight simply calculated inversely proportional to the effective area of each class is adopted to achieve fairer training. Note that our weights are more flexible as they can be adaptively adjusted along with the optimizing features during training. Experiments on four long-tailed datasets show that the proposed weights outperform the state-of-the-art reweighting methods. Moreover, our method can also achieve better results on statistically balanced CIFAR-10/100. Code is available at https://github.com/xiaohua-chen/AREA.

Recently, sequence generation methods are widely used in complex named entity recognition. By selecting high-related tokens to generate complex named entities, these methods obtain several achievements. However, due to lack of guidance in learning output format and ignoring labels in obtaining features, sequence generation methods suffer invalid output and inaccurate recognition. To solve that, we propose an Enhancing Entity Representation method with Prompt Guidance (ERPG). Specifically, in order to reduce invalid output, we design the candidate entity generation module that generate candidate entities and their labels as expected. Besides, to accurately recognize candidate entities, we propose candidate entity refine module, which obtain distinguishable candidate entity representations and filter them accurately. Based on that, our method finally outperforms baselines by 1.20, 1.62 and 0.69 F1 scores in ACE2004, GENIA and CADEC corpora, which proves the effectiveness in complex named entity recognition.

Relation extraction is extracting relational facts between target entities from plain text. It has attracted much interest and achieved improvement from research communities recently. However, effectively capturing relational information while ignoring intra-sentence noise from the text remains a challenge. To this end, we propose a novel RAN (Relation-aware Network) model for relation extraction. The basic idea of RAN is to model relation features, providing more accurate guidance for directly capturing relational information in a sentence, and improving the performance of relation extraction. Specifically, we first propose a multi-channel relation representation learning module. This module studies dependencies between the target entity pair in multiple sub-channels to model relation vectors. Then a dual attention mechanism-based relational words selection module is designed to highlight the relational information in the sentence of different dimensions, including semantic- and syntactic-level features. We evaluate our model on two public datasets: SemEval-2010 Task 8 and TACRED. Experiments on two benchmark datasets demonstrate the inspiring performance improvement over state-of-the-art models.

Cross-network node classification aims to leverage the abundant knowledge from a labeled source network to help classify the node in an unlabeled target network. However, existing methods assume that label sets are identical across domains, which is easily violated in practice. Hence, we attempt to integrate network embedding with universal domain adaptation, which transfers valuable knowledge across domains without assumption on the label sets, to assist in node classification. Nonetheless, the complex network relationships between nodes increase the difficulty of this universal domain adaptive node classification task. In this work, we propose a novel Universal Domain Adaptive Network Embedding (UDANE) framework, which learns transferable node representations across networks to succeed in such a task. Technically, we first adopt the cross-network node embedding component to model comprehensive node information of both networks. Then we employ the inter-domain adaptive alignment component to exploit and relate knowledge across domains, learning domain-invariant representation for knowledge transfer. In addition, the intra-domain contrastive alignment component is proposed to learn discriminative representations beneficial for classification by sufficiently utilizing unlabeled data in the target domain. Extensive experiments have been conducted on real-world datasets, demonstrating that the proposed UDANE model outperforms the state-of-the-art baselines by a large margin.

Incremental learning for person re-identification (ReID) aims to develop models that can be trained with a continuous data stream, which is a more practical setting for real-world applications. However, the existing incremental ReID methods make two strong assumptions that the cameras are fixed and the new-emerging data is class-disjoint from previous classes. This is unrealistic as previously observed pedestrians may re-appear and be captured again by new cameras. In this paper, we investigate person ReID in an unexplored scenario named Camera Incremental Person ReID (CIPR), which advances existing lifelong person ReID by taking into account the class overlap issue. Specifically, new data collected from new cameras may probably contain an unknown proportion of identities seen before. This subsequently leads to the lack of cross-camera annotations for new data due to privacy concerns. To address these challenges, we propose a novel framework ExtendOVA. First, to handle the class overlap issue, we introduce an instance-wise seen-class identification module to discover previously seen identities at the instance level. Then, we propose a criterion for selecting confident ID-wise candidates and also devise an early learning regularization term to correct noise issues in pseudo labels. Furthermore, to compensate for the lack of previous data, we resort prototypical memory bank to create surrogate features, along with a cross-camera distillation loss to further retain the inter-camera relationship. The comprehensive experimental results on multiple benchmarks show that ExtendOVA significantly outperforms the state-of-the-arts with remarkable advantages.

With the extensive utilization of deep hashing, there exists a surging interest in studying adversarial attacks against it. Previous methods have demonstrated the superior white-box attack performance against deep hashing. However, the more challenging and realistic targeted black-box attack has not yet been explored sufficiently, which will result in an over-estimation on model robustness. In this paper, we focus on targeted black-box attack based on transferability, and propose a novel Targeted Transferable Attack method against deep hashing with Generative Adversarial Network (TTA-GAN). Specifically, we first propose a new Iterative Anchor code Optimization (IAO) method to generate anchor code with superior representative semantics of target label, which can improve both targeted white-box and black-box performances. Then, we propose a generation-based method to directly generate targeted transferable adversarial example by training a conditional generator and a discriminator. Moreover, to further promote the targeted transferability, we conduct multiple input transformations on the generated adversarial example to alleviate the overfitting phenomenon on source model. Finally, we extend our method to a novel model ensemble attack method TTA-GANens to preserve the representative semantics on multiple models, specialized for deep hashing. Extensive experiments demonstrate the superior targeted black-box attack performance than the state-of-the-art methods.

The deepening of digital transformation has led to an increasing amount of data from industries being transmitted over the Internet. However, packets in plaintext originally designed for transmission in private networks suffer from significant security threats on the Internet. Unfortunately, existing encryption schemes, such as the representative TLS, are difficult to be applied to these industrial protocols due to their specific requirements and conditions such as low latency requirements and restricted operating environments. In this paper, we present a high-performance encryption/decryption middlebox called GuardBox to provide confidentiality and integrity for packets. GuardBox is expected to transparently encrypt/decrypt packets sent/received by protected industrial equipment with low latency and supports almost any application-layer protocol. To do that, we design a high-performance packet I/O framework and an optimized encryption/decryption scheme for GuardBox. More importantly, we use commodity trusted hardware, Intel SGX, to ensure the security of keys and the encryption/decryption process. Our extensive evaluation demonstrates that GuardBox can provide confidentiality and integrity for packets transmitted over the Internet with low latency and a near-native throughput.

Website fingerprinting is exploited to analyze encrypted traffic traces and infer the visited website. Existing website fingerprinting methods can achieve satisfying performance for the HTTP traffic visiting websites over TCP. Recently, a new protocol QUIC has been proposed, and HTTP-over-QUIC has been formalized as the next generation HTTP, named HTTP/3. Thus, it is necessary to classify HTTP/3 traces. However, since HTTP/3 is newly proposed and is being deployed, it is difficult to collect a large number of HTTP/3 traces. Intuitively, we can use sufficient TCP traces to improve the performance of the QUIC trace classifier. Unfortunately, the protocol discrepancy exists between TCP and QUIC traces, which undermines the generalization ability of the classifier. In this paper, for practical website fingerprinting of HTTP/3, we propose a Website-Aware Protocol Confusion Network (WAPCN), which exploits only a few QUIC traces to train a website classifier with the help of lots of available TCP traces. It consists of four main parts: a feature extractor, a website classifier, a protocol discriminator, and a website-aware adaptor. The feature extractor aims to extract trace representations from both TCP and QUIC traces. It cooperates with the website classifier to learn the discriminative representation for the website classification. The role of the protocol discriminator is to confuse protocols and guide the feature extractor to learn protocol-invariant representations. The website-aware adaptor can enhance protocol-invariant representations to be aware of the website classification boundary. Extensive experiments are conducted on various tasks to demonstrate the effectiveness of WAPCN.

Hashing has been drawing increasing attention in the task of large-scale image retrieval owing to its storage and computation efficiency, especially the recent asymmetric deep hashing methods. These approaches treat the query and database in an asymmetric way and can take full advantage of the whole training data. Though it has achieved state-of-the-art performance, asymmetric deep hashing methods still suffer from the large quantization error and efficiency problem on large-scale datasets due to the tight coupling between the query and database. In this article, we propose a novel asymmetric hashing method, called D eep U ncoupled D iscrete H ashing (DUDH), for large-scale approximate nearest neighbor search. Instead of directly preserving the similarity between the query and database, DUDH first exploits a small similarity-transfer image set to transfer the underlying semantic structures from the database to the query and implicitly keep the desired similarity. As a result, the large similarity matrix is decomposed into two relatively small ones and the query is decoupled from the database. Then both database codes and similarity-transfer codes are directly learned during optimization. The quantization error of DUDH only exists in the process of preserving similarity between the query and similarity-transfer set. By uncoupling the query from the database, the training cost of optimizing the CNN model for the query is no longer related to the size of the database. Besides, to further accelerate the training process, we propose to optimize the similarity-transfer codes with a constant-approximation solution. In doing so, the training cost of optimizing similarity-transfer codes can be almost ignored. Extensive experiments on four widely used image retrieval benchmarks demonstrate that DUDH can achieve state-of-the-art retrieval performance with remarkable training cost reduction (30× - 50× relative).

Denial of service (DoS) attacks have increasingly exploited vulnerabilities in algorithms or implementation methods in application-layer programs. In this type of attack, called CPU-exhaustion DoS attack, a few well-crafted requests may consume a lot of server resources, which is essentially different from traditional volumetric DoS attacks. Due to the lack of recognizable patterns, the traditional network-layer defense mechanism is usually unable to detect such sophisticated DoS attacks. In this paper, we proposeCoda, a framework for detecting application-layer CPU-exhaustion DoS attacks in containers.Codamonitors the CPU time consumed by each connection and uses statistical methods to detect attacks. It traces system calls and other related information from the container based on Linux eBPF at the host level. Some specific system calls are used to indicate the establishment and closure of the connection, which in turn indicate the start/end of the request processing. After triggering these specific system calls,Codastarts/ends monitoring the CPU time consumed by a connection. An attack can be detected when the CPU time consumed by an attack connection is statistically different from that consumed by a legitimate connection.Codahas the following key advantages. First, it works with programs built in different programming languages. Second, it remains agnostic to the source code of protected programs. Third, it supports monitoring the container and is transparent to the container. Through evaluation of real-world attacks, we demonstrate thatCodacan accurately detect ongoing application-layer CPU-exhaustion DoS attacks with low additional overhead.

Real-world data often follows a long-tailed distribution, which makes the performance of existing classification algorithms degrade heavily. A key issue is that the samples in tail categories fail to depict their intra-class diversity. Humans can imagine a sample in new poses, scenes and view angles with their prior knowledge even if it is the first time to see this category. Inspired by this, we propose a novel reasoning-based implicit semantic data augmentation method to borrow transformation directions from other classes. Since the covariance matrix of each category represents the feature transformation directions, we can sample new directions from similar categories to generate definitely different instances. Specifically, the long-tailed distributed data is first adopted to train a backbone and a classifier. Then, a covariance matrix for each category is estimated, and a knowledge graph is constructed to store the relations of any two categories. Finally, tail samples are adaptively enhanced via propagating information from all the similar categories in the knowledge graph. Experimental results on CIFAR-LT-100, ImageNet-LT, and iNaturalist 2018 have demonstrated the effectiveness of our proposed method compared with the state-of-the-art methods.

Hamming space retrieval can achieve constant-time image search, which is more efficient than linear scan. In Hamming space retrieval, the data points inside the Hamming ball imply retrievable while the data points outside are irretrievable. Therefore, it is crucial to explicitly characterize the Hamming ball. However, for the existing Hamming space retrieval methods, many similar points are found close to the outside of the Hamming ball while many dissimilar points are found close to the query point, leading to the decline of both retrieval accuracy and recall. In this paper, we present a novel method named Deep Piecewise Hashing (DPH), for Efficient Hamming Space Retrieval. A piecewise loss is elaborately designed to guide the learning of hash codes. Meanwhile, a piecewise probability distribution is introduced in the proposed loss function. The piecewise probability distribution pays more attention to the learning of those "marginal" similar points. It considers both discrimination and robustness for the dissimilar points inside the Hamming ball. Comprehensive experiments on two datasets, MS-COCO and NUS-WIDE, demonstrate that DPH can yield state-of-the-art Hamming space retrieval performance.

Person re-identification (ReID) aims at retrieving images of the same person across non-overlapping camera views. The prior works focus on either fully supervised or unsupervised ReID settings, and achieve remarkable performances. In real scenarios, however, the major annotation cost comes from matching identity classes across camera views, thus leading to the Intra-Camera Supervised (ICS) ReID problem. In this work, we propose a Prototype-based Inter-camera ReID (PIRID) method, which tackles the ICS setting through the lens of prototype learning. Specifically, we first introduce the intra-camera learning with non-parametric classifiers to separately generate discriminative features within each camera view. Moreover, the inter-camera prototype learning provides prototypes as the representatives of each class in the common space, making the learned features to be camera-agnostic. Experiments conducted on three benchmarks, i.e., Market-1501, DukeMTMC-ReID, and MSMT17, show the superiority of our method.

The lack of supervised information is the pivotal problem in unsupervised hashing. Most methods leverage deep features extracted from pre-trained models to generate semantic similarities as supervised information. These fixed features are, however, neither designed originally for retrieval nor updated adaptively during training. In this paper, we propose a novel deep Unsupervised Cluster and Separate Hashing (UCSH) to address these issues. Specifically, we introduce a fully end-to-end deep hashing network with a binary latent Variational AutoEncoder (VAE), which enables hash codes capable of reconstructing deep features as well as preserving semantic relations. Moreover, a ‘Cluster and Separate’ scheme is proposed to jointly cluster deep features and separate semantic similarities. Both the implicit feature clustering and the explicit similarity separating loss encourage the separation of similar and dissimilar pairs, enabling the iteratively updated similarities to better excavate semantic relations. Experiments conducted on three benchmarks show the superiority of UCSH.

Video is a natural source of multi-modal data with intrinsic correlations between different modalities, such as objects, motions and captions. Though intuitive, such inherent supervision has not been well explored in previous video-audio retrieval works. Besides, existing methods exploit the video stream and the audio stream seperately, whereas ignoring the mutual interactions between them. In this paper, we propose a two-stream model named Multi-modal Aggregation and Co-attention network (MAC), which processes video and audio inputs with co-attentional interactions. Specifically, our method takes raw videos as inputs and extracts aggregated features from multiple modalities to benefit the video representation learning. Then, we introduce the self-attention mechanism to make videos adaptively assign higher weights to the representative modalities. Moreover, we introduce a coattention transformer module to better capture the relations among videos and audios. By exchanging key-value pairs in the multi-headed attention, this module enables video-attended audio features to be incorporated into video representations and vice versa. Experiments show that our method significantly outperform other state-of-the-arts.

Relation extraction is the task of extracting relational facts between entities from plain text. When the extraction scope is extended to the document level, entities may exist in dif-ferent sentences. This requires the model to consider the in-teraction between multiple sentences comprehensively. Thus, document-level relation extraction becomes especially chal-lenging. Most existing models adopt entity representation learning to tackle this challenge. Nevertheless, they gener-ally perform representations of individual entities rather than directly modeling the dependencies between entities reflect target relation, which may cause wrong relation reasoning. To solve this issue, we propose a novel dual reasoning-based pairwise representation network. Specifically, we perform the semantic and syntactic-based reasoning to model the associ-ation between entities, and towards the capture of relational information in the document through an unique contextual se-lection for each entity pair. Experiments on three benchmark datasets demonstrate the inspiring performance improvement over state-of-the-art relation extraction models.

Sequential recommendations can dynamically model user interests, which has great value since users' interests may change rapidly with time. Traditional sequential recommendation methods assume that the user behaviors are rigidly ordered and sequentially dependent. However, some user behaviors have flexible orders, meaning the behaviors may occur in any order and are not sequentially dependent. Therefore, traditional methods may capture inaccurate user interests based on wrong dependencies. Motivated by this, several methods identify flexible orders by continuity or similarity. However, these methods fail to comprehensively understand the nature of flexible orders since continuity or similarity do not determine order flexibilities. Therefore, these methods may misidentify flexible orders, leading to inappropriate recommendations. To address these issues, we propose a Flexible Order aware Sequential Recommendation (FOSR) method to identify flexible orders comprehensively. We argue that orders' flexibilities are highly related to the frequencies of item pair co-occurrences. In light of this, FOSR employs a probabilistic based flexible order evaluation module to simulate item pair frequencies and infer accurate order flexibilities. The frequency labeling module extracts labels from the real item pair frequencies to guide the order flexibility measurement. Given the measured order flexibilities, we develop a flexible order aware self-attention module to model dependencies from flexible orders comprehensively and learn dynamic user interests effectively. Extensive experiments on four benchmark datasets show that our model outperforms various state-of-the-art sequential recommendation methods.

Person re-identification~(Re-ID) aims at retrieving the same person across the non-overlapped camera networks. Recent works have achieved impressive performance due to the rapid development of deep learning techniques. However, most existing methods have ignored the practical unbalanced property in real-world Re-ID scenarios. In fact, the number of pedestrian images in different cameras vary a lot. Some cameras cover thousands of images while others only have a few. As a result, the camera-unbalanced problem will reduce intra-camera diversity, then the model cannot learn camera-invariant features to distinguish pedestrians from "poor" cameras. In this paper, we design a novel camera-specific informative data augmentation module~(CIDAM) to alleviate the proposed camera-unbalanced problem. Specifically, we first calculate the camera-specific distribution online, then refine the "poor" camera-specific covariance matrix with similar cameras defined in the prototype-based similarity matrix. Consequently, informative augmented samples are generated by combining original samples with sampled random vectors in feature space. To ensure these augmented samples can better benefit the model training, we further propose a dynamic-threshold-based contrastive loss. Since augmented samples may not be as real as original ones, we calculate a threshold for each original one dynamically and only push hard negative augmented samples away. Moreover, our CIDAM can be compatible with a variety of existing Re-ID methods. Extensive experiments prove the effectiveness of our method.

Person Re-IDentification (ReID) aims at retrieving images of the same person across multiple camera views. Despite its popularity in surveillance and public safety, the leakage of identity information is still at risk. For example, once obtaining the illegal access to ReID systems, malicious user can accurately retrieve the target person, leading to the exposure of private information. Recently, some pioneering works protect private images with adversarial examples by adding imperceptible perturbations to target images. However, in this paper, we argue that directly applying adversary-based methods to protect the ReID system is sub-optimal due to the 'overlap identity' issue. Specifically, merely pushing the adversarial image away from its original label would probably make it move into the vicinity of other identities. This leads to the potential risk of being retrieved when querying with all the other identities exhaustively. We thus propose a novel preemptive-Protection person Re-IDentification (PRIDE) method. By explicitly constraining the adversarial image to an isolated location, the target person is far away from neither the original identity nor any other identities, which protects him from being retrieved by illegal queries. Moreover, we further propose two crucial attack scenarios (Random Attack and Order Attack) and a novel Success Protection Rate (SPR) metric to quantify the protection ability. Experiments show consistent outperformance of our method over other baselines across different ReID models, datasets and attack scenarios.

Deep hashing methods have been intensively studied and successfully applied in large-scale multimedia retrieval. In real-world scenarios, code length can not be set once for all if retrieval accuracy is not satisfying. However, when code length increases, conventional deep hashing methods have to retrain their models and regenerate the whole database codes, which is impractical for large-scale retrieval system. In this paper, we propose an interesting deep hashing method from a brand new perspective, called Code Expansion oriented Deep Hashing (CEDH). Different from conventional deep hashing methods, our CEDH focuses on the fast expansion of existing hash codes. Instead of regenerating all bits from raw images, the new bits in CEDH can be incrementally learned by recycling the old ones. Specifically, we elaborately design an end-to-end asymmetric framework to simultaneously optimize a CNN model for query images and a code projection matrix for database images. With the learned code projection matrix, hash codes can achieve fast expansion through simple matrix multiplication. Subsequently, a novel code expansion hashing loss is proposed to preserve the similarities between query codes and expanded database codes. Due to the loose coupling in our framework, our CEDH is compatible with a variety of deep hashing methods. Moreover, we propose to adopt smooth similarity matrix to solve "similarity contradiction" problem existing in multi-label image datasets, thus further improving our performance on multi-label datasets. Extensive experiments on three widely used image retrieval benchmarks demonstrate that CEDH can significantly reduce the cost for expanding database codes (about 100,000x faster with GPU and 1,000,000x faster with CPU) when code length increases while keeping the state-of-the-art retrieval accuracy. Our code is available at https://github.com/IIE-MMR/2022MM-CEDH.

Nowadays, the leakage of personal information and privacy becomes a major concern in various fields, such as social sciences, genomics, and medicine. To combat this problem, differential privacy has been proposed and soon be widely studied and applied. Meanwhile, the compositional nature of differential privacy has motivated the design and implementation of differentially private machine learning mechanisms. However, as these mechanisms are gradually deployed in practice, a serious problem appears: they find it hard to choose a meaningful ε value or understand the meaning of a chosen ε value in practice. To this end, we propose a novel and efficient approach that would allow users to choose ε according to their utility or accuracy requirement. Specifically, we can efficiently obtain the expected ε value that would generate a private model satisfying the expected empirical loss or expected accuracy, through at least one-round training and some calculations. As product requirements often impose hard accuracy constraints, our approach allows users to focus on their own benefits without paying too much attention to things they don’t understand or care. Both theoretical analysis and experimental results demonstrate high accuracy and broad applicability of our mechanism in practical applications.

Recently, deep semi-supervised hashing methods have attracted increasing attention, which can significantly improve retrieval performance by leveraging abundant unlabeled data. These methods usually generate surrogate supervision signals to learn with unlabeled data, such as neighborhood information and augmentation invariant requirements. However, an essential issue of these methods is that the supervised signals are not always reliable, which may damage the performance. In this paper, we propose a novel Uncertainty-Aware and Multi-Granularity Consistent Constrained Semi-Supervised Hashing (UMCSH) method to alleviate the negative effects of noisy supervised signals and enlarge the inter-class distance. Specifically, our UMCSH mainly consists of an Uncertainty-Aware Instance-Level Consistency (UAILC) model and a Cluster-Based Class-Level Consistency (CBCLC) model. UAILC introduces an uncertainty estimation method to select reliable supervised signals to extract discriminative features for each unlabeled data. CBCLC establishes connections between labeled data and unlabeled data by encouraging each unlabeled sample to be close to the hash center (calculated with the labeled data) according to its pseudo-label. Extensive experimental results demonstrate the superior performance of our proposed approach compared with several state-of-the-art semi-supervised hashing methods.

Recently, deep semi-supervised hashing methods have attracted increasing attention, where the visual similarity of unlabeled data is usually adopted to guide the hash codes learning. However, samples with similar appearance may come from different categories, making their hash codes similar will lead to sub-optimal retrieval results. In this paper, we propose a novel Disturbance Consistent Self-Ensembling (DCSE) method to alleviate the drawback of visual similarity constraint. Specially, DCSE forms consensus hash codes for the same sample under different augmentations. These ensemble hash codes can capture the discriminative characteristics of a sample. Therefore, as more augmented data is involved, more ensemble hash codes in one category can become similar gradually. Then, we design a disturbance consistent loss to learn the discriminative hash codes by minimizing the distance between outputs of the hash layer and ensemble hash codes. Extensive experiments show that our proposed approach significantly outperforms state-of-the-art semi-supervised hashing methods.

Cross-modal video-text retrieval has been an emerging task due to the rapid growth of user-generated videos on the Internet. Most existing approaches focus on extracting visual feature for the video, while audio and caption on the screen containing rich information are ignored. Recently, the aggregations of multi-modal features in videos boost the benchmark of video-text retrieval. However, since these multi-modal features are high-dimensional and heterogeneous, their intrinsically structural relations have not been attached with enough importance and are often overlooked in previous methods. To address this issue, we propose a novel Attentive and Relational Feature Aggregation Network (ARFAN). Specifically, we introduce the self-attention mechanism to make videos adaptively assign higher weights to the representative modalities. Then, the graph convolutional layers are inserted to capture the relations among the multi-modal features to combine them. Our method achieves 15% and 12.9% relative improvements on R@1 when compared with the state-of-the-art method on MSR-VTT and MSVD datasets, respectively.

Deep hashing methods have shown great retrieval accuracy and efficiency in large-scale image retrieval. How to optimize discrete hash bits is always the focus in deep hashing methods. A common strategy in these methods is to adopt an activation function, e.g. sigmoid() or tanh(), and minimize a quantization loss to approximate discrete values. However, this paradigm may make more and more hash bits stuck into the wrong saturated area of the activation functions and never escaped. We call this problem "Dead Bits Problem (DBP)". Besides, the existing quantization loss will aggravate DBP as well. In this paper, we propose a simple but effective gradient amplifier which acts before activation functions to alleviate DBP. Moreover, we devise an error-aware quantization loss to further alleviate DBP. It avoids the negative effect of quantization loss based on the similarity between two images. The proposed gradient amplifier and error-aware quantization loss are compatible with a variety of deep hashing methods. Experimental results on three datasets demonstrate the efficiency of the proposed gradient amplifier and the error-aware quantization loss.

Community search, also known as local community detection, is designed to obtain the community structure containing the given query nodes. At present, community search technology has been widely studied, but most of them ignore the effect of node attributes. Some studies propose attributed community search methods and usually adopt a two-phase approach. Generally, the subgraph with structure cohesiveness is obtained first and then the subgraph with keyword cohesiveness is returned as the final result on this basis. In practice, approaches of this kind may lead to incomplete or incorrect results, because information from one single aspect cannot accurately describe the feature of nodes. That is, topology information and attribute information of the network should be complementary. In this paper, we propose an attributed community model called RCS(Representation-based Community Search). Firstly we apply random-walk based representation learning technology to combine topology information and attribute information of nodes. Secondly we propose a new community model to formulate the problem that what is a good community based on the representation information. Then a series of algorithms are designed to fetch a cohesive community whose vertices are tightly connected and closely related to query nodes. Finally the effectiveness and efficiency of RCS are verified by extensive experiments on several real-world networks with ground-truth cnmmunities.

Heterogeneous side information has been widely used in recommender systems to alleviate the data sparsity problem. However, the heterogeneous side information in existing methods provides insufficient guidance for predicting user preferences as its effect is inevitably weakened during utilization. Furthermore, most existing methods cannot effectively utilize the heterogeneous side information to understand users and items. They often neglect the interrelation among various types of heterogeneous side information of a user or an item. As a result, it is difficult for existing methods to comprehensively understand users and items so that the recommender system recommends inappropriate items to users. To overcome the above drawbacks, we propose an interrelation learning-based recommendation method with iterative heterogeneous side information guidance (ILIG). ILIG includes two modules: 1) Iterative Heterogeneous Side Information Guidance Module. It uses heterogeneous side information to iteratively guide the prediction of user preferences, which effectively enhances the effect of the heterogeneous side information. 2) Interrelation Learning-based Portrait Construction Module. It captures the interrelation among various types of heterogeneous side information to comprehensively learn the representations of users and items. To demonstrate the effectiveness of ILIG, we conduct extensive experiments on Movielens-100K, Movielens-1M, and BookCrossing datasets. The experimental results show that ILIG outperforms the state-of-the-art recommender systems.

Cross-modal retrieval between videos and texts has attracted growing attention due to the rapid growth of user-generated videos on the web. To solve this problem, most approaches try to learn a joint embedding space to measure the cross-modal similarities, while paying little attention to the representation of each modality. Video is more complicated than the commonly used visual feature, since the audio and caption on the screen also contain rich information. Recently, the aggregations of multiple features in videos boost the benchmark of the video-text retrieval system. However, they usually handle each feature independently, which ignores the interchange of high-level semantic relations among these multiple features. Moreover, despite the inter-modal ranking constraint where semantically-similar texts and videos should stay closer, the modality-specific requirement, i.e. two similar videos/texts should have similar representations, is also significant. In this paper, we propose a novel Multi-Feature Graph ATtention Network (MFGATN) for cross-modal video-text retrieval. Specifically, we introduce a multi-feature graph attention module, which enriches the representation of each feature in videos with the interchange of high-level semantic information among them. Moreover, we elaborately design a novel Dual Constraint Ranking Loss (DCRL), which simultaneously considers the inter-modal ranking constraint and the intra-modal structure constraint to preserve both the cross-modal semantic similarity and the modality-specific consistency in the embedding space. Experiments on two datasets, i.e. MSR-VTT and MSVD, demonstrate that our method achieves significant performance gain compared with the state-of-the-arts.

Hashing has become increasingly important for large-scale image retrieval, of which the low storage cost and fast searching are two key properties. However, existing methods adopt large neural networks, which are hard to be deployed in resource-limited devices due to the unacceptable memory and runtime overhead. We address that this huge overhead of neural networks somewhatviolates the appealing properties of hashing. In this paper, we propose a novel deep hashing method, called Binary Neural Network Hashing (BNNH) for fast image retrieval. Specifically, we construct an efficient binarized network architecture to provide lighter model and faster inference, which directly generates binary outputs as the desired hash codes without introducing the quantization loss. Besides, in order to circumvent the huge performance degradation caused by the extremely quantized activations, we introduce a simple yet effective activation-aware loss to explicitly guide the updating of activations in intermediate layers. Extensive experiments conducted on three benchmarks show that the proposed method outperforms the state-of-the-art binarization methods by large margins and validate the efficiency of BNNH.

Traditional implementations of differential privacy implicitly assume that users have homogeneous privacy requirement for all attributes of data. They provide a uniform level of privacy guarantee for all attributes by using a single privacy budget,$\varepsilon$. However, this brings trouble to users in practice applications, where privacy requirements are often heterogeneous. In this case, users have to make a choice: either setting the privacy level high enough to satisfy even the privacy fundamentalists, which often results in poor model utility, or sacrificing the privacy of some attributes for practical model. Both are hard to be accepted by users. In this paper, we offer users what they probably want, an option that could provide a satisfactory privacy guarantee for important attributes with minimal utility loss. Our method, called heterogeneous differentially private ERM (HDP-ERM), allows the private learning algorithms to guarantee heterogeneous privacy for each attribute of training data. The noise injected in each parameter is adaptive according to its individual privacy budget, so that we can control the privacy-utility trade-off more finely. Experimental results show that our method is able to reach a satisfactory utility when only the important attributes need strong privacy guarantee, while the traditional DP-ERM would only get a useless model (one with low test accuracy) when providing the same level of privacy guarantee.

Given a network and a set of seeds related to each other, the problem of relation discovery from focusing seeds aims to discover the relations among all the seeds. Due to its wide applications, the task has been well studied in the literature. However, when facing applications where maybe not all the seeds relate to each other, methods for the task will discover many vertices unrelated to the seeds. To support such applications, a new problem called adaptive relation discovery from focusing seeds (A-RDFS) is proposed and studied in this article. Given a network and a set of seeds that may not be related to each other, discover additional vertices to reveal the relations among the seeds which are related to each other. To solve the A-RDFS problem, a relation sensitive subgraph structure called the α- relation core is proposed to find vertices related to a subset of the seeds. Thereafter, a metric called the relation quality is proposed to measure the quality of discovered relations. The metric is positively correlated with the α value of each discovered α-relation core. Hence, by maximizing the relation quality, a set of α-relation cores with large α values can be discovered, which reveals the relations among the seeds related to each other. Two algorithms are developed to optimize the relation quality. Then, using the algorithms as subroutines, the OPT-A-RDFS method is designed for the A-RDFS problem. Extensive experimental results demonstrate the performance of our methods.

Recently, face image hashing has been proposed in large-scale face image retrieval due to its storage and computational efficiency. However, owing to the large intra-identity variation (same identity with different poses, illuminations, and facial expressions) and the small inter-identity separability (different identities look similar) of face images, existing face image hashing methods have limited power to generate discriminative hash codes. In this work, we propose a deep hashing method specially designed for face image retrieval named deep Discrete Attention Guided Hashing (DAGH). In DAGH, the discriminative power of hash codes is enhanced by a well-designed discrete identity loss, where not only the separability of the learned hash codes for different identities is encouraged, but also the intra-identity variation of the hash codes for the same identities is compacted. Besides, to obtain the fine-grained face features, DAGH employs a multi-attention cascade network structure to highlight discriminative face features. Moreover, we introduce a discrete hash layer into the network, along with the proposed modified backpropagation algorithm, our model can be optimized under discrete constraint. Experiments on two widely used face image retrieval datasets demonstrate the inspiring performance of DAGH over the state-of-the-art face image hashing methods.

Deep hashing methods have achieved tremendous success in cross-modal retrieval, due to its low storage consumption and fast retrieval speed. In real cross-modal retrieval applications, it's hard to obtain label information. Recently, increasing attention has been paid to unsupervised cross-modal hashing. However, existing methods fail to exploit the intrinsic connections between images and their corresponding descriptions or tags (text modality). In this paper, we propose a novel Deep Semantic-Alignment Hashing (DSAH) for unsupervised cross-modal retrieval, which sufficiently utilizes the co-occurred image-text pairs. DSAH explores the similarity information of different modalities and we elaborately design a semantic-alignment loss function, which elegantly aligns the similarities between features with those between hash codes. Moreover, to further bridge the modality gap, we innovatively propose to reconstruct features of one modality with hash codes of the other one. Extensive experiments on three cross-modal retrieval datasets demonstrate that DSAH achieves the state-of-the-art performance.

Hashing has become increasingly important for large-scale image retrieval. Recently, deep supervised hashing has shown promising performance, yet little work has been done under the more realistic unsupervised setting. The most challenging problem in unsupervised hashing methods is the lack of supervised information. Besides, existing methods fail to distinguish image pairs with different similarity degrees, which leads to a suboptimal construction of similarity matrix. In this paper, we propose a simple yet effective unsupervised hashing method, dubbed Deep Unsupervised Hybrid-similarity Hadamard Hashing (DU3H), which tackles these issues in an end-to-end deep hashing framework. DU3H employs orthogonal Hadamard codes to provide auxiliary supervised information in unsupervised setting, which can maximally satisfy the independence and balance properties of hash codes. Moreover, DU3H utilizes both highly and normally confident image pairs to jointly construct a hybrid-similarity matrix, which can magnify the impacts of different pairs to better preserve the semantic relations between images. Extensive experiments conducted on three widely used benchmarks validate the superiority of DU3H.

Benefiting from recent advances in deep learning, deep hashing methods have achieved promising performance in large-scale image retrieval. To improve storage and computational efficiency, existing hash codes need to be compressed accordingly. However, previous deep hashing methods have to retrain their models and then regenerate the whole database codes using the new models when code length changes, which is time consuming especially for large image databases. In this paper, we propose a novel deep hashing method, called Code Compression oriented Deep Hashing (CCDH), for efficiently compressing hash codes. CCDH learns deep hash functions for query images, while learning a one-hidden-layer Variational Autoencoder (VAE) from existing hash codes. With such asymmetric design, CCDH can efficiently compress database codes only using the learned encoder of VAE. Furthermore, CCDH is flexible enough to be used with a variety of deep hashing methods. Extensive experiments on three widely used image retrieval benchmarks demonstrate that CCDH can significantly reduce the cost for compressing database codes when code length changes while keeping the state-of-the-art retrieval accuracy.

As a major kind of query-dependent community detection, community search finds a densely connected subgraph containing a set of query nodes. As density is the major consideration of community search, most methods of community search often find a dense subgraph with many vertices far from the query nodes, which are not very related to the query nodes. Motivated by this, a new problem called community focusing (CF) is studied. It finds a community where the members are close and densely connected to the query nodes. A distance-sensitive dense subgraph structure called β-attention-core is proposed to remove the vertices loosely connected to or far from the query nodes, and a combinational density is designed to guarantee the density of a subgraph. Then CF is formalized as finding a subgraph with the largest combinational density among the β-attention-core subgraphs containing the query nodes with the largest β. Thereafter, effective methods are devised for CF. Furthermore, a speed-up strategy is developed to make the methods scalable to large networks. Extensive experimental results on real and synthetic networks demonstrate the performance of our methods.

Hashing has shown great potential in large-scale image retrieval due to its storage and computation efficiency, especially the recent deep supervised hashing methods. To achieve promising performance, deep supervised hashing methods require a large amount of training data from different classes. However, when images of new categories emerge, existing deep hashing methods have to retrain the CNN model and generate hash codes for all the database images again, which is impractical for large-scale retrieval system. In this paper, we propose a novel deep hashing framework, called Deep Incremental Hashing Network (DIHN), for learning hash codes in an incremental manner. DIHN learns the hash codes for the new coming images directly, while keeping the old ones unchanged. Simultaneously, a deep hash function for query set is learned by preserving the similarities between training points. Extensive experiments on two widely used image retrieval benchmarks demonstrate that the proposed DIHN framework can significantly decrease the training time while keeping the state-of-the-art retrieval accuracy.

Cross-modal hashing has attracted considerable attention for large-scale multimodal retrieval task. A majority of hashing methods have been proposed for cross-modal retrieval. However, these methods inadequately focus on feature learning process and cannot fully preserve higher-ranking correlation of various item pairs as well as the multi-label semantics of each item, so that the quality of binary codes may be downgraded. To tackle these problems, in this paper, we propose a novel deep cross-modal hashing method, called Adversary Guided Asymmetric Hashing (AGAH). Specifically, it employs an adversarial learning guided multi-label attention module to enhance the feature learning part which can learn discriminative feature representations and keep the cross-modal invariability. Furthermore, in order to generate hash codes which can fully preserve the multi-label semantics of all items, we propose an asymmetric hashing method which utilizes a multi-label binary code map that can equip the hash codes with multi-label semantic information. In addition, to ensure higher-ranking correlation of all similar item pairs than those of dissimilar ones, we adopt a new triplet-margin constraint and a cosine quantization technique for Hamming space similarity preservation. Extensive empirical studies show that AGAH outperforms several state-of-the-art methods for cross-modal retrieval.

Deep supervised hashing methods for multi-label image retrieval have achieved great success nowadays. However, these methods only take the similarity between the database images and the query images into account, but they ignore the uniqueness of the database images when deciding on their rankings. Here we present a novel Deep Uniqueness-Aware Hashing (DUAH) method for learning hash functions that preserve not only multilevel semantic similarity between multi-label images, but also the unique semantic structure of each image. In our approach, both the pairwise label information and the classification information are fully exploited to maximize the discriminability of the output binary codes within one stream framework. Extensive evaluations conducted on three widely used multi-label image benchmarks demonstrate that DUAH can support fine-grained multi-label image retrieval better.

Deep hashing methods have achieved promising results for large-scale image retrieval recently. To accelerate the subsequent Hamming ranking process, the multi-index approach has been proposed to reduce the computations for the Hamming distance. However, the binary codes output by the previous deep hashing methods may not be optimally compatible with the multi-index approach. In this paper, we present a novel Deep Index-Compatible Hashing (DICH) method for fast image retrieval, which can learn similarity-preserving binary codes that are more compatible with the multi-index approach. With the learned binary codes, both the size of the intermediate result set produced by the multi-index approach and the number of the candidate images can be reduced, which can accelerate the Hamming ranking process. By taking advantage of the unique feature of DICH, we further propose a block-based ranking strategy to quickly rank the candidate images without calculating the Hamming distance. Extensive evaluations demonstrate that the proposed method can significantly reduce the retrieval time with almost no loss of retrieval accuracy.

One of the most challenging tasks in large-scale multi-label image retrieval is to map images into binary codes while preserving multilevel semantic similarity. Recently, several deep supervised hashing methods have been proposed to learn hash functions that preserve multilevel semantic similarity with deep convolutional neural networks. However, these triplet label based methods try to preserve the ranking order of images according to their similarity degrees to the queries while not putting direct constraints on the distance between the codes of very similar images. Besides, the current evaluation criteria are not able to measure the performance of existing hashing methods on preserving fine-grained multilevel semantic similarity. To tackle these issues, we propose a novel Deep Multilevel Semantic Similarity Preserving Hashing (DMSSPH) method to learn compact similarity-preserving binary codes for the huge body of multi-label image data with deep convolutional neural networks. In our approach, we make the best of the supervised information in the form of pairwise labels to maximize the discriminability of output binary codes. Extensive evaluations conducted on several benchmark datasets demonstrate that the proposed method significantly outperforms the state-of-the-art supervised and unsupervised hashing methods at the accuracies of top returned images, especially for shorter binary codes. Meanwhile, the proposed method shows better performance on preserving fine-grained multilevel semantic similarity according to the results under the Jaccard coefficient based evaluation criteria we propose.

ABSTRACT A new steganographic method for data hiding in Microsoft Word 2007–2010 (Microsoft Corp., Redmond, WA, USA) files that use Office Open XML (OOXML) format is proposed. Secret information can be imperceptibly embedded into OOXML documents by splitting up the printable text, which is defined by the main document body of the OOXML format document. The number of printable words contained in each segment represents the secret message. Theoretical analysis demonstrates that embedding bit rate of the proposed method can take the maximum value (0.8) when 2 bits of secret message are embedded into each segment. Experiments show that 0.44 bit is embedded into each word and 1/151 bit is embedded into each bit of the document on average, which is higher than contemporary linguistic steganography approaches. The method can resist “Format”, “Impersonation”, “Save As”, “Copy”, and other active attacks, and all these changes will not be shown on the MS Office screen display. Therefore, the proposed method can apply to the fields of covert communication and security protection for OOXML format documents. Copyright © 2011 John Wiley & Sons, Ltd.