Related papers: Boosting Adversarial Transferability of MLP-Mixer
Malware has been one of the most damaging threats to computers that span across multiple operating systems and various file formats. To defend against ever-increasing and ever-evolving malware, tremendous efforts have been made to propose a…
In recent years, despite significant advancements in adversarial attack research, the security challenges in cross-modal scenarios, such as the transferability of adversarial attacks between infrared, thermal, and RGB images, have been…
Although great progress has been made on adversarial attacks for deep neural networks (DNNs), their transferability is still unsatisfactory, especially for targeted attacks. There are two problems behind that have been long overlooked: 1)…
Adversarial attacks are a central tool for probing the robustness of modern vision models, yet most methods optimize perturbations directly in pixel space under $\ell_\infty$ or $\ell_2$ constraints. While effective in white-box settings,…
We present a new method for black-box adversarial attack. Unlike previous methods that combined transfer-based and scored-based methods by using the gradient or initialization of a surrogate white-box model, this new method tries to learn a…
The rapid progress of Multi-Modal Large Language Models (MLLMs) has significantly advanced downstream applications. However, this progress also exposes serious transferable adversarial vulnerabilities. In general, existing adversarial…
Nowadays, digital facial content manipulation has become ubiquitous and realistic with the success of generative adversarial networks (GANs), making face recognition (FR) systems suffer from unprecedented security concerns. In this paper,…
The multi-agent reinforcement learning systems (MARL) based on the Markov decision process (MDP) have emerged in many critical applications. To improve the robustness/defense of MARL systems against adversarial attacks, the study of various…
Transfer-based attacks pose a significant threat to real-world applications by directly targeting victim models with adversarial examples generated on surrogate models. While numerous approaches have been proposed to enhance adversarial…
Deep neural networks(DNNs) is vulnerable to be attacked by adversarial examples. Black-box attack is the most threatening attack. At present, black-box attack methods mainly adopt gradient-based iterative attack methods, which usually limit…
We consider a wireless communication system that consists of a transmitter, a receiver, and an adversary. The transmitter transmits signals with different modulation types, while the receiver classifies its received signals to modulation…
This paper substantially extends our work published at ECCV, in which an intermediate-level attack was proposed to improve the transferability of some baseline adversarial examples. Specifically, we advocate a framework in which a direct…
The vulnerability of deep neural networks (DNNs) to adversarial examples has drawn great attention from the community. In this paper, we study the transferability of such examples, which lays the foundation of many black-box attacks on…
A wireless communications system usually consists of a transmitter which transmits the information and a receiver which recovers the original information from the received distorted signal. Deep learning (DL) has been used to improve the…
Several moving target defenses (MTDs) to counter adversarial ML attacks have been proposed in recent years. MTDs claim to increase the difficulty for the attacker in conducting attacks by regularly changing certain elements of the defense,…
Machine learning systems based on deep neural networks, being able to produce state-of-the-art results on various perception tasks, have gained mainstream adoption in many applications. However, they are shown to be vulnerable to…
Transferability of adversarial examples is of critical importance to launch black-box adversarial attacks, where attackers are only allowed to access the output of the target model. However, under such a challenging but practical setting,…
Adversarial attacks can readily disrupt the image classification system, revealing the vulnerability of DNN-based recognition tasks. While existing adversarial perturbations are primarily applied to uncompressed images or compressed images…
Strong adversarial examples are crucial for evaluating and enhancing the robustness of deep neural networks. However, the performance of popular attacks is usually sensitive, for instance, to minor image transformations, stemming from…
The field of adversarial robustness has long established that adversarial examples can successfully transfer between image classifiers and that text jailbreaks can successfully transfer between language models (LMs). However, a pair of…