21 June 2023 in IEEE Transactions on Information Forensics and Security
Deep neural networks are known to be vulnerable to adversarial examples, where adding carefully crafted adversarial perturbations to the inputs can mislead the DNN model. However, it is challenging to generate effective adversarial examples in the physical world due to many uncontrollable physical dynamics, which pose security and safety threats in the real world. Current physical attack methods aim to generate robust physical adversarial examples by simulating all possible physical dynamics. If attacking a new image or a new DNN model, they require expensive manual efforts for simulating physical dynamics or considerable time for iteratively optimizing. To tackle these limitations, we propose a robust and generalized physical adversarial attack method with Meta-GAN (Meta-GAN Attack), which is able to not only generate robust physical adversarial examples, but also generalize to attacking novel images and novel DNN models by accessing a few digital and physical images. First, we propose to craft robust physical adversarial examples with a generative attack model via simulating color and shape distortions. Second, we formulate the physical attack as a few-shot learning problem and design a novel class-agnostic and model-agnostic meta-learning algorithm to solve this problem. Extensive experiments on two benchmark datasets with four challenging experimental settings verify the superior robustness and generalization of our method by comparing to state-of-the-art physical attack methods. The source code is released at github.
26 June 2024 in International Journal of Computer Vision
15 January 2024 in IEEE Transactions on Multimedia
Adversarial examples are well known to pose a security risk, when attacking deep learning models. While, most of existing adversarial attacks are designed to attack a single deep learning-based task, such as image classification. In practical scenarios, it is more necessary to study adversarial examples transferring across different vision tasks. However, it is challenging to create cross-task adversarial examples that can destroy multiple vision tasks at once due to unavailable various task-specific models and loss functions for attackers. To deal with this problem, we propose a Dual Attention-Guided Method (DAGM) for crafting cross-task adversarial examples by designing a spatial attention module and a channel attention module to capture overlapping discriminative regions and features that contribute to various tasks. Then we craft cross-task adversarial examples via reducing the dispersion ( i.e. , standard deviation) of feature maps re-weighted by both attention modules, which can destroy the overlapping discriminative regions and features for various tasks. Furthermore, to present theoretical explanation, we systematically analyze our method, and rigorously prove that both attention modules can provide better effectiveness of our adversarial examples, compared with existing cross-task adversarial attacks. Extensive experiments on two datasets demonstrate that our method can significantly degrade the performance of various tasks, even online CV APIs, and consistently outperform state-of-the-art methods by a large margin.
8 July 2020 in IEEE Transactions on Communications
As a promising candidate for future Internet architecture, Named Data Networking (NDN) can achieve significant potential advantages over current TCP/IP based Internet in content distribution and mobility support, etc. However, the communication mode in NDN that one Interest packet for pulling one data packet is likely to incur Interest packets flooding and to cause extremely large-scale Pending Interest Table (PIT) of the NDN router, which may substantially degrade the performance of NDN. Moreover, the absence of predefined connections also induces another challenge for NDN to manage the successive and concurrent requests from consumers efficiently. In this paper, we propose flow-based NDN (f-NDN) architecture capable of supporting flow transmission mode for addressing the aforementioned challenges. In the context of f-NDN, a data flow is defined as an aggregate of data packets with the same name prefix, and a flow Interest packet is introduced to pull a data flow rather than a single data packet. The PIT, CS, and FIB are re-designed to enable f-NDN to operate at the granularity of flows. Bitmap structure aided error handling mechanism is further presented for f-NDN to deal with the flow transmission’s uncertain failures. The built-in flow support in f-NDN allows us to conceive a flow-level multi-path transmission regime for balancing the traffic in NDN network and reducing the time consumed for pulling the entire content. Weight-based flow Interest splitting algorithm and optimal rate control algorithm are both proposed for optimizing multi-path transmission. We illustrate the capability of the proposed architecture in supporting flow transmission and multi-path by implementing it in both simulator and prototype systems. The evaluation results are also presented to show its achievable performance.
25 March 2024 in IEEE Transactions on Information Forensics and Security
Despite the rapid progress and significant success of deep learning in a wide spectrum of fields, adversarial examples expose many security threats to deep learning models. Recently, an interesting property has been discovered that adversarial examples are transferable, which means adversarial examples targeting a given model can also attack another model. Therefore, many researchers are attracted by this property and work on how to improve the transferability of adversarial examples. Furthermore, compared to the traditional attack methods of disrupting output logits (dubbed logit-based attacks), recent works reveal that disrupting feature maps instead of logits can lead to more transferable adversarial examples (dubbed feature-based attacks). However, previous feature-based attacks mostly hold the intuitive designs of the optimization goals and specialization for certain scenarios with a lack of theoretical motivations and a unified framework. To overcome these limitations, we propose a Unified Feature-based Attack Framework, dubbed as UFAF, combining a dispersion loss and a distance loss, which unifies eight existing feature-based attacks. Furthermore, we also bridge the formulation gap between feature-based attacks and traditional logit-based attacks. With our UFAF, we propose an Entropy-Wasserstein (EW) attack by specifying the dispersion loss as Entropy and the distance loss as Wasserstein Distance, respectively. Besides, we provide theoretical analysis to guarantee the effectiveness of the proposed attack method. Extensive experimental results show the superior performance of our EW attack, which can outperform state-of-the-art attacks by 4.95% on attack success rates in untargeted attack settings, and by 1.95% on targeted transfer rates and 1.17% on target success rates in targeted attack settings. Moreover, our framework can help other feature-based attacks improve their performance by 7.7% in untargeted attack settings.