相关论文: Logit Pairing Methods Can Fool Gradient-Based Atta…

Misaligned research objectives have considerably hindered progress in adversarial robustness research over the past decade. For instance, an extensive focus on optimizing target metrics, while neglecting rigorous standardized evaluation,…

Deep learning is vulnerable to adversarial examples. Many defenses based on randomized neural networks have been proposed to solve the problem, but fail to achieve robustness against attacks using proxy gradients such as the Expectation…

With the boom of Large Language Models (LLMs), the research of solving Math Word Problem (MWP) has recently made great progress. However, there are few studies to examine the security of LLMs in math solving ability. Instead of attacking…

Federated learning (FL) is a privacy-preserving distributed framework for collaborative model training on devices in edge networks. However, challenges arise due to vulnerability to adversarial examples (AEs) and the non-independent and…

The deep neural networks are known to be vulnerable to well-designed adversarial attacks. The most successful defense technique based on adversarial training (AT) can achieve optimal robustness against particular attacks but cannot…

Deep networks are well-known to be fragile to adversarial attacks. We conduct an empirical analysis of deep representations under the state-of-the-art attack method called PGD, and find that the attack causes the internal representation to…

Adversarial attacks, particularly the Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) pose significant threats to the robustness of deep learning models in image classification. This paper explores and refines defense…

In this work we study input gradient regularization of deep neural networks, and demonstrate that such regularization leads to generalization proofs and improved adversarial robustness. The proof of generalization does not overcome the…

Finite mixtures of classifiers (a.k.a. randomized ensembles) have been proposed as a way to improve robustness against adversarial attacks. However, existing attacks have been shown to not suit this kind of classifier. In this paper, we…

While machine-learning algorithms have demonstrated a strong ability in detecting Android malware, they can be evaded by sparse evasion attacks crafted by injecting a small set of fake components, e.g., permissions and system calls, without…

Robustness evaluation against adversarial examples has become increasingly important to unveil the trustworthiness of the prevailing deep models in natural language processing (NLP). However, in contrast to the computer vision domain where…

Large language models (LLMs) are increasingly deployed as educational agents for automatic short answer grading (ASAG) in real-world educational environments, significantly boosting assessment efficiency and scalability. However, when these…

Federated learning faces increasing threats from model poisoning attacks, which harms its application to improve privacy. Existing defense methods typically rely on fixed thresholds or perform clustering with a fixed number of clusters to…

The ability of machine learning (ML) classification models to resist small, targeted input perturbations -- known as adversarial attacks -- is a key measure of their safety and reliability. We show that floating-point non-associativity…

Adversarial training is an effective approach to make deep neural networks robust against adversarial attacks. Recently, different adversarial training defenses are proposed that not only maintain a high clean accuracy but also show…

Model robustness against adversarial examples of single perturbation type such as the $\ell_{p}$-norm has been widely studied, yet its generalization to more realistic scenarios involving multiple semantic perturbations and their…

Traditional (fickle) adversarial examples involve finding a small perturbation that does not change an input's true label but confuses the classifier into outputting a different prediction. Conversely, obstinate adversarial examples occur…

Generative adversarial networks (GANs) are one of the most popular approaches when it comes to training generative models, among which variants of Wasserstein GANs are considered superior to the standard GAN formulation in terms of learning…

Adversarial attack has recently become a tremendous threat to deep learning models. To improve the robustness of machine learning models, adversarial training, formulated as a minimax optimization problem, has been recognized as one of the…

Safe Reinforcement learning (Safe RL) aims at learning optimal policies while staying safe. A popular solution to Safe RL is shielding, which uses a logical safety specification to prevent an RL agent from taking unsafe actions. However,…