An official website of the United States government
The pervasiveness of neural networks (NNs) in critical computer vision and image processing applications makes them very attractive for adversarial manipulation. A large body of existing research thoroughly investigates two broad categories of attacks targeting the integrity of NN models. The first category of attacks, commonly called Adversarial Examples, perturbs the model's inference by carefully adding noise into input examples. In the second category of attacks, adversaries try to manipulate the model during the training process by implanting Trojan backdoors. Researchers show that such attacks pose severe threats to the growing applications of NNs and propose several defenses against each attack type individually. However, such one-sided defense approaches leave potentially unknown risks in real-world scenarios when an adversary can unify different attacks to create new and more lethal ones bypassing existing defenses. In this work, we show how to jointly exploit adversarial perturbation and model poisoning vulnerabilities to practically launch a new stealthy attack, dubbed AdvTrojan. AdvTrojan is stealthy because it can be activated only when: 1) a carefully crafted adversarial perturbation is injected into the input examples during inference, and 2) a Trojan backdoor is implanted during the training process of the model. We leverage adversarial noise in the input space to move Trojan-infected examples across the model decision boundary, making it difficult to detect. The stealthiness behavior of AdvTrojan fools the users into accidentally trusting the infected model as a robust classifier against adversarial examples. AdvTrojan can be implemented by only poisoning the training data similar to conventional Trojan backdoor attacks. Our thorough analysis and extensive experiments on several benchmark datasets show that AdvTrojan can bypass existing defenses with a success rate close to 100% in most of our experimental scenarios and can be extended to attack federated learning as well as high-resolution images.
more »
« less
Stochastic Computing as a Defence Against Adversarial Attacks
Abstract- Neural networks (NNs) are increasingly often employed in safety critical systems. It is therefore necessary to ensure that these NNs are robust against malicious interference in the form of adversarial attacks, which cause an NN to misclassify inputs. Many proposed defenses against such attacks incorporate randomness in order to make it harder for an attacker to find small input modifications that result in misclassification. Stochastic computing (SC) is a type of approximate computing based on pseudo-random bit-streams that has been successfully used to implement convolutional neural networks (CNNs). Some results have previously suggested that such stochastic CNNs (SCNNs) are partially robust against adversarial attacks. In this work, we will demonstrate that SCNNs do indeed possess inherent protection against some powerful adversarial attacks. Our results show that the white-box C&W attack is up to 16x less successful compared to an equivalent binary NN, and Boundary Attack even fails to generate adversarial inputs in many cases.
more »
« less
- Award ID(s):
- 2006704
- PAR ID:
- 10518941
- Publisher / Repository:
- IEEE
- Date Published:
- ISBN:
- 979-8-3503-2543-0
- Page Range / eLocation ID:
- 191 to 194
- Format(s):
- Medium: X
- Location:
- Porto, Portugal
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Vision transformers (ViTs) have recently set off a new wave in neural architecture design thanks to their record-breaking performance in various vision tasks. In parallel, to fulfill the goal of deploying ViTs into real-world vision applications, their robustness against potential malicious attacks has gained increasing attention. In particular, recent works show that ViTs are more robust against adversarial attacks as compared with convolutional neural networks (CNNs), and conjecture that this is because ViTs focus more on capturing global interactions among different input/feature patches, leading to their improved robustness to local perturbations imposed by adversarial attacks. In this work, we ask an intriguing question: “Under what kinds of perturbations do ViTs become more vulnerable learners compared to CNNs?” Driven by this question, we first conduct a comprehensive experiment regarding the robustness of both ViTs and CNNs under various existing adversarial attacks to understand the underlying reason favoring their robustness. Based on the drawn insights, we then propose a dedicated attack framework, dubbed Patch-Fool, that fools the self-attention mechanism by attacking its basic component (i.e., a single patch) with a series of attention-aware optimization techniques. Interestingly, our Patch-Fool framework shows for the first time that ViTs are not necessarily more robust than CNNs against adversarial perturbations. In particular, we find that ViTs are more vulnerable learners compared with CNNs against our Patch-Fool attack which is consistent across extensive experiments, and the observations from Sparse/Mild Patch-Fool, two variants of Patch-Fool, indicate an intriguing insight that the perturbation density and strength on each patch seem to be the key factors that influence the robustness ranking between ViTs and CNNs. It can be expected that our Patch-Fool framework will shed light on both future architecture designs and training schemes for robustifying ViTs towards their real-world deployment. Our codes are available at https://github.com/RICE-EIC/Patch-Fool.more » « less
-
Large-scale deep neural networks are both memory and computation-intensive, thereby posing stringent requirements on the computing platforms. Hardware accelerations of deep neural networks have been extensively investigated. Spe- cific forms of binary neural networks (BNNs) and stochastic computing-based neural networks (SCNNs) are particularly appealing to hardware implementations since they can be im- plemented almost entirely with binary operations. Despite the obvious advantages in hardware implementation, these approximate computing techniques are questioned by researchers in terms of accuracy and universal applicability. Also it is important to understand the relative pros and cons of SCNNs and BNNs in theory and in actual hardware im- plementations. In order to address these concerns, in this pa- per we prove that the ”ideal” SCNNs and BNNs satisfy the universal approximation property with probability 1 (due to the stochastic behavior), which is a new angle from the orig- inal approximation property. The proof is conducted by first proving the property for SCNNs from the strong law of large numbers, and then using SCNNs as a “bridge” to prove for BNNs. Besides the universal approximation property, we also derive an appropriate bound for bit length M in order to pro- vide insights for the actual neural network implementations. Based on the universal approximation property, we further prove that SCNNs and BNNs exhibit the same energy com- plexity. In other words, they have the same asymptotic energy consumption with the growth of network size. We also pro- vide a detailed analysis of the pros and cons of SCNNs and BNNs for hardware implementations and conclude that SC- NNs are more suitable.more » « less
-
Profiled side-channel analysis (SCA) leverages leakage from cryptographic implementations to extract the secret key. When combined with advanced methods in neural networks (NNs), profiled SCA can successfully attack even those cryptocores assumed to be protected against SCA. Despite the rise in the number of studies devoted to NN-based SCA, a range of questions has remained unanswered, namely: how to choose an NN with an adequate configuration, how to tune the NN’s hyperparameters, when to stop the training, etc. Our proposed approach, “InfoNEAT,” tackles these issues in a natural way. InfoNEAT relies on the concept of neural structure search, enhanced by information-theoretic metrics to guide the evolution, halt it with novel stopping criteria, and improve time-complexity and memory footprint. The performance of InfoNEAT is evaluated by applying it to publicly available datasets composed of real side-channel measurements. In addition to the considerable advantages regarding the automated configuration of NNs, InfoNEAT demonstrates significant improvements over other approaches for effective key recovery in terms of the number of epochs (e.g.,x6 faster) and the number of attack traces compared to both MLPs and CNNs (e.g., up to 1000s fewer traces to break a device) as well as a reduction in the number of trainable parameters compared to MLPs (e.g., by the factor of up to 32). Furthermore, through experiments, it is demonstrated that InfoNEAT’s models are robust against noise and desynchronization in traces.more » « less
-
Current deep neural networks (DNNs) are vulnerable to adversarial attacks, where adversarial perturbations to the inputs can change or manipulate classification. To defend against such attacks, an effective and popular approach, known as adversarial training (AT), has been shown to mitigate the negative impact of adversarial attacks by virtue of a min-max robust training method. While effective, it remains unclear whether it can successfully be adapted to the distributed learning context. The power of distributed optimization over multiple machines enables us to scale up robust training over large models and datasets. Spurred by that, we propose distributed adversarial training (DAT), a large-batch adversarial training framework implemented over multiple machines. We show that DAT is general, which supports training over labeled and unlabeled data, multiple types of attack generation methods, and gradient compression operations favored for distributed optimization. Theoretically, we provide, under standard conditions in the optimization theory, the convergence rate of DAT to the first-order stationary points in general non-convex settings. Empirically, we demonstrate that DAT either matches or outperforms state-of-the-art robust accuracies and achieves a graceful training speedup (e.g., on ResNet–50 under ImageNet).more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/DSN-W58399.2023.00053
