Open source software supply-chain attacks, once successful, can exact heavy costs in mission-critical applications. As open source ecosystems for deep learning flourish and become increasingly universal, they present attackers previously unexplored avenues to code-inject malicious backdoors in deep neural network models. This article proposes Flareon , a small, stealthy, seemingly harmless code modification that specifically targets the data augmentation pipeline with motion-based triggers. Flareon neither alters ground-truth labels, nor modifies the training loss objective, nor does it assume prior knowledge of the victim model architecture, training data, and training hyperparameters. Yet, it has a surprisingly large ramification on training—models trained under Flareon learn powerful target-conditioned (or “ all2all ”) backdoors. We also proposed a learnable variant of Flareon that is even stealthier in terms of added perturbations. The resulting models can exhibit high attack success rates for any target choices and better clean accuracies than backdoor attacks that not only seize greater control but also assume more restrictive attack capabilities. We also demonstrate the resilience of Flareon against a wide range of defenses. Flareon is fully open source and available online to the deep learning community.

Federated Learning (FL) enables multiple devices to collaboratively train a shared model while preserving data privacy. Most existing research assumes that all participating devices have sufficient resources to support the training process. However, the high memory requirements of model training present a significant challenge to deploying FL on resource-constrained devices in practical scenarios. To this end, this paper presents ProFL, a new framework that effectively addresses the memory constraints in FL. Rather than updating the full model during local training, ProFL partitions the model into blocks based on its original architecture and trains each block in a progressive fashion. It first trains the front blocks and safely freezes them after convergence. Training of the next block is then triggered. This process progressively grows the model to be trained until the training of the full model is completed. In this way, the peak memory footprint is effectively reduced for feasible deployment on heterogeneous devices. In order to preserve the feature representation of each block, the training process is divided into two stages: model shrinking and model growing. During the model shrinking stage, we meticulously design corresponding output modules to assist each block in learning the expected feature representation and obtain the initialization model parameters. Subsequently, the obtained output modules and initialization model parameters are utilized in the corresponding model growing stage, which progressively trains the full model. Additionally, a novel metric from the scalar perspective is proposed to assess the learning status of each block, enabling us to securely freeze it after convergence and initiate the training of the next one. Finally, we theoretically prove the convergence of ProFL and conduct extensive experiments on representative models and datasets to evaluate its effectiveness. The results demonstrate that ProFL effectively reduces the peak memory footprint by up to 57.4% and improves model accuracy by up to 82.4%.

With the rapid development of large language models (LLMs), there has been a strong interest in integrating other modalities such as image comprehension capabilities. While they have shown impressive performance in various multimodal tasks, the robustness of Visual Language Models (VLMs) has not been thoroughly investigated. We mainly focus on the robustness of VLMs on visual adversarial examples. In this work, we explore the capability of adversarial examples targeting VLMs. We highlight that the multimodal nature of VLMs presents a unique attack surface to manipulate the outputs of the LLMs, and the continuous nature of visual inputs further enhances the effectiveness of adversarial attacks against language generative models. Furthermore, we demonstrate three application scenarios for adversarial examples targeting VLMs: image description, jailbreaking, and information hiding. We conduct experiments on several leading open-source VLMs and demonstrate the successful application of adversarial examples in all the proposed scenarios. We hope that our findings would enable the development of multimodal models more robust to adversarial attacks. Our code is available at https://github.com/lafeat/m3-break.

Automated Feature Engineering (AFE) refers to automatically generate and select optimal feature sets for downstream tasks, which has achieved great success in real-world applications. Current AFE methods mainly focus on improving the effectiveness of the produced features, but ignoring the low-efficiency issue for large-scale deployment. Therefore, in this work, we propose a generic framework to improve the efficiency of AFE. Specifically, we construct the AFE pipeline based on reinforcement learning setting, where each feature is assigned an agent to perform feature transformation and selection, and the evaluation score of the produced features in downstream tasks serve as the reward to update the policy. We improve the efficiency of AFE in two perspectives. On the one hand, we develop a Feature Pre-Evaluation (FPE) Model to reduce the sample size and feature size that are two main factors on undermining the efficiency of feature evaluation. On the other hand, we devise a two-stage policy training strategy by running FPE on the pre-evaluation task as the initialization of the policy to avoid training policy from scratch. We conduct comprehensive experiments on 36 datasets in terms of both classification and regression tasks. The results show 2.9% higher performance in average and 2x higher computational efficiency comparing to state-of-the-art AFE methods.

The cold-start problem, faced when providing recommendations to newly joined users with no historical interaction record existing in the platform, is one of the most critical problems that negatively impact the performance of a recommendation system. Fortunately, cross-domain recommendation~(CDR) is a promising approach for solving this problem, which can exploit the knowledge of these users from source domains to provide recommendations in the target domain. However, this method requires that the central server has the interaction behaviour data in both domains of all the users, which prevents users from participating due to privacy issues.

One of the most popular location privacy-preserving mechanisms applied in location-based services (LBS) is location obfuscation, where mobile users are allowed to report obfuscated locations instead of their real locations to services. Many existing obfuscation approaches consider mobile users that can move freely over a region. However, this is inadequate for protecting the location privacy of vehicles, as their mobility is restricted by external factors, such as road networks and traffic flows. This auxiliary information about external factors helps an attacker to shrink the search range of vehicles' locations, increasing the risk of location exposure.

Transfer learning through fine-tuning a pre-trained neural network with an extremely large dataset, such as ImageNet, can significantly improve and accelerate training while the accuracy is frequently bottlenecked by the limited dataset size of the new target task. To solve the problem, some regularization methods, constraining the outer layer weights of the target network using the starting point as references (SPAR), have been studied. In this article, we propose a novel regularized transfer learning framework \operatorname{DELTA} , namely DE ep L earning T ransfer using Feature Map with A ttention . Instead of constraining the weights of neural network, \operatorname{DELTA} aims at preserving the outer layer outputs of the source network. Specifically, in addition to minimizing the empirical loss, \operatorname{DELTA} aligns the outer layer outputs of two networks, through constraining a subset of feature maps that are precisely selected by attention that has been learned in a supervised learning manner. We evaluate \operatorname{DELTA} with the state-of-the-art algorithms, including L^2 and \emph {L}^2\text{-}SP . The experiment results show that our method outperforms these baselines with higher accuracy for new tasks. Code has been made publicly available. 1

Urban traffic network is a typical complex network. Traffic states data (e.g., traffic flow, traffic occupancy, traffic speed, etc.) has strong temporal and spatial correlation. To accurately predict urban traffic state, it is very important to extract the road features in the traffic network. The existing methods use separated temporal and spatial components or Spatio-temporal fusion components to predict traffic. Graph Convolution Network (GCN) is usually used to obtain the correlation between spatial nodes or Spatio-temporal nodes. However, the message aggregation method of GCN cannot assign different weights to neighbor nodes. While Graph Attention Network (GAT) can pay attention to different neighbor nodes. To better explain the existing traffic prediction models, we carried out experiments on the model framework based on GCN. We use a new proposed GAT instead of GCN, and find that the new GAT has better performance in multi-features traffic prediction tasks. We also made a theoretical analysis on the improvement of the performance and carried out experiments on four real datasets, which can provide strong support for the theoretical analysis. Our method improves the interpretability of the Graph Neural Network (GNN) model in extracting spatial features of the traffic networks.

Ensemble learning is a widely used technique to train deep convolutional neural networks (CNNs) for improved robustness and accuracy. While existing algorithms usually first train multiple diversified networks and then assemble these networks as an aggregated classifier, we propose a novel learning paradigm, namely, “In-Network Ensemble” ( INE ) that incorporates the diversity of multiple models through training a SINGLE deep neural network. Specifically, INE segments the outputs of the CNN into multiple independent classifiers, where each classifier is further fine-tuned with better accuracy through a so-called diversified knowledge distillation process . We then aggregate the fine-tuned independent classifiers using an Averaging-and-Softmax operator to obtain the final ensemble classifier. Note that, in the supervised learning settings, INE starts the CNN training from random, while, under the transfer learning settings, it also could start with a pre-trained model to incorporate the knowledge learned from additional datasets. Extensive experiments have been done using eight large-scale real-world datasets, including CIFAR, ImageNet, and Stanford Cars, among others, as well as common deep network architectures such as VGG, ResNet, and Wide ResNet. We have evaluated the method under two tasks: supervised learning and transfer learning. The results show that INE outperforms the state-of-the-art algorithms for deep ensemble learning with improved accuracy.

Stochastic Gradient Langevin Dynamics (SGLD) have been widely used for Bayesian sampling from certain probability distributions, incorporating derivatives of the log-posterior. With the derivative evaluation of the log-posterior distribution, SGLD methods generate samples from the distribution through performing as a thermostats dynamics that traverses over gradient flows of the log-posterior with certainly controllable perturbation. Even when the density is not known, existing solutions still can first learn the kernel density models from the given datasets, then produce new samples using the SGLD over the kernel density derivatives. In this work, instead of exploring new samples from kernel spaces, a novel SGLD sampler, namely, Randomized Measurement Langevin Dynamics (RMLD) is proposed to sample the high-dimensional sparse representations from the spectral domain of a given dataset. Specifically, given a random measurement matrix for sparse coding, RMLD first derives a novel likelihood evaluator of the probability distribution from the loss function of LASSO, then samples from the high-dimensional distribution using stochastic Langevin dynamics with derivatives of the logarithm likelihood and Metropolis–Hastings sampling. In addition, new samples in low-dimensional measuring spaces can be regenerated using the sampled high-dimensional vectors and the measurement matrix. The algorithm analysis shows that RMLD indeed projects a given dataset into a high-dimensional Gaussian distribution with Laplacian prior, then draw new sparse representation from the dataset through performing SGLD over the distribution. Extensive experiments have been conducted to evaluate the proposed algorithm using real-world datasets. The performance comparisons on three real-world applications demonstrate the superior performance of RMLD beyond baseline methods.

Traffic bottlenecks identification plays an important role in traffic planning and provides decision-making for prevention of traffic congestion. Although traffic bottlenecks widely exist, they are difficult to predict because of the changing traffic condition and traffic demand. In this paper, we introduce a traffic congestion diffusion (TCD) model with traffic flow influence (TFI) to capture the traffic dynamics and give a panoramic view for the city by cross domain data fusion. We proposed novel definition of bottleneck from the perspective of influence spread under TCD. The bottlenecks identification problem is modeled as an influence maximization problem, i.e., selecting the top K influential nodes in road networks under certain traffic conditions. We establish the submodularity of influence spread and solve the NP-hard optimal seed selection problem by using an efficient heuristic algorithm (TCD-IM) with provable near-optimal performance guarantees. To the best of our knowledge, this should be the first model for a metro-city scale from the influence perspective. The TCD-IM model is able to identify the dynamic traffic bottlenecks.

To improve resource efficiency and design intelligent scheduler for clouds, it is necessary to understand the workload characteristics and machine utilization in large-scale cloud data centers. In this paper, we perform a deep analysis on a newly released trace dataset by Alibaba in September 2017, consists of detail statistics of 11089 online service jobs and 12951 batch jobs co-locating on 1300 machines over 12 hours. To the best of our knowledge, this is one of the first work to analyze the Alibaba public trace. Our analysis reveals several important insights about different types of imbalance in the Alibaba cloud. Such imbalances exacerbate the complexity and challenge of cloud resource management, which might incur severe wastes of resources and low cluster utilization. 1) Spatial Imbalance: heterogeneous resource utilization across machines and workloads. 2) Temporal Imbalance: greatly time-varying resource usages per workload and machine. 3) Imbalanced proportion of multi-dimensional resources (CPU and memory) utilization per workload. 4) Imbalanced resource demands and runtime statistics (duration and task number) between online service and offline batch jobs. We argue accommodating such imbalances during resource allocation is critical to improve cluster efficiency, and will motivate the emergence of new resource managers and schedulers.

Traffic congestion is a spatio-temporal state of speeds beyond the capacity of road design and congestion may propagate through road networks. Characterizing the diffusion process is of great importance both in congestion relief and traffic condition prediction. Traffic congestion diffusion (TCD) in road networks can be observed, but literature lacks accurate models for characterizing the process. In this paper, we define a concept of Traffic Flow Influence (TFI) as a base for congestion diffusion. A TCD model is designed to characterize not only the traffic flow evolving process in time domain but also the propagation process of TFI through road networks in space domain. The model is for traffic networks in a city, which is divided into grids and each grid is modeled by traffic status of congested or smooth. Different from other diffusion models, the grid status depends on not only its current condition, but also the relative traffic flow from and to its neighbors. We use a gradient descent approach to quantify the traffic flow and TFI intensity of road networks. To the best of our knowledge, this should be the first model for a metro-city scale. The TCD model with TFI is able to predict grid status with an accuracy as high as 89%. Experimental results based on real-world taxi trajectory data in a metro-city show that the TCD approach performs best in comparison with its competitors.

In an IMANET, mobile users access both text and media web contents on the Internet through gateway nodes, with web access patterns, i.e., the Zipf-like distribution or the Stretched Exponential distribution. To reduce data access delay from the Internet, we consider the cache placement problem in cooperative caching, which is that each mobile node selects a subset of web contents to cache cooperatively in its limited cache so that total access cost is minimized. It has been proved NP-hard. We propose a solution named Adaptive Allocation Cooperative Caching (AACC), which adaptively divides the cache space of each node into two components: altruistic and selfish, according to detected data access patterns. AACC aims to find the optimal cache allocation solution to allocate appropriate cache spaces for two components in order to minimize total access cost. Given the Zipf-like access distribution, we find a near-optimal allocation solution to the cache placement problem. Simulation results show that AACC achieves much better performance than the existing best cooperative caching strategy in IMANETs in terms of average query delay, caching overheads, and query success ratio. In particular, AACC reduces caching overheads by 40% in average.

Recently, big data has been evolved into a buzzword from academia to industry all over the world. Benchmarks are important tools for evaluating an IT system. However, benchmarking big data systems is much more challenging than ever before. First, big data systems are still in their infant stage and consequently they are not well understood. Second, big data systems are more complicated compared to previous systems such as a single node computing platform. While some researchers started to design benchmarks for big data systems, they do not consider the redundancy between their benchmarks. Moreover, they use artificial input data sets rather than real world data for their benchmarks. It is therefore unclear whether these benchmarks can be used to precisely evaluate the performance of big data systems. In this paper, we first analyze the redundancy among benchmarks from ICTBench, HiBench and typical workloads from real world applications: spatio-temporal data analysis for Shenzhen transportation system. Subsequently, we present an initial idea of a big data benchmark suite for spatio-temporal data. There are three findings in this work: (1) redundancy exists in these pioneering benchmark suites and some of them can be removed safely. (2) The workload behavior of trajectory data analysis applications is dramatically affected by their input data sets. (3) The benchmarks created for academic research cannot represent the cases of real world applications.

Prefetching is an important technique to reduce the average Web access latency. Existing prefetching methods are based mostly on URL graphs. They use the graphical nature of HTTP links to determine the possible paths through a hypertext system. Although the URL graph-based approaches are effective in prefetching of frequently accessed documents, few of them can prefetch those URLs that are rarely visited. The paper presents a keyword-based semantic prefetching approach to overcome the limitation. It predicts future requests based on semantic preferences of past retrieved Web documents. We apply this technique to Internet news services and implement a client-side personalized prefetching system: NewsAgent. The system exploits semantic preferences by analyzing keywords in URL anchor text of previously accessed documents in different news categories. It employs a neural network model over the keyword set to predict future requests. The system features a self-learning capability and good adaptability to the change of client surfing interest. NewsAgent does not exploit keyword synonymy for conservativeness in prefetching. However, it alleviates the impact of keyword polysemy by taking into account server-provided categorical information in decision-making and, hence, captures more semantic knowledge than term-document literal matching methods. Experimental results from daily browsing of ABC News, CNN, and MSNBC news sites for a period of three months show an achievement of up to 60 percent hit ratio due to prefetching.