Related papers: Understanding Adversarial Transfer: Why Representa…
Despite the substantial advancements in Vision-Language Pre-training (VLP) models, their susceptibility to adversarial attacks poses a significant challenge. Existing work rarely studies the transferability of attacks on VLP models,…
Adversarial attacks and backdoor attacks are two common security threats that hang over deep learning. Both of them harness task-irrelevant features of data in their implementation. Text style is a feature that is naturally irrelevant to…
As neural networks become the tool of choice to solve an increasing variety of problems in our society, adversarial attacks become critical. The possibility of generating data instances deliberately designed to fool a network's analysis can…
Large Language Models (LLMS) have increasingly become central to generating content with potential societal impacts. Notably, these models have demonstrated capabilities for generating content that could be deemed harmful. To mitigate these…
The integration of new modalities enhances the capabilities of multimodal large language models (MLLMs) but also introduces additional vulnerabilities. In particular, simple visual jailbreaking attacks can manipulate open-source MLLMs more…
Machine learning models are vulnerable to both security attacks (e.g., adversarial examples) and privacy attacks (e.g., private attribute inference). We take the first step to mitigate both the security and privacy attacks, and maintain…
Transferability of adversarial samples became a serious concern due to their impact on the reliability of machine learning system deployments, as they find their way into many critical applications. Knowing factors that influence…
An intriguing property of deep neural networks is the existence of adversarial examples, which can transfer among different architectures. These transferable adversarial examples may severely hinder deep neural network-based applications.…
Vision Transformers are increasingly embedded in industrial systems due to their superior performance, but their memory and power requirements make deploying them to edge devices a challenging task. Hence, model compression techniques are…
It has recently been shown that adversarial attacks on large language models (LLMs) can "jailbreak" the model into making harmful statements. In this work, we argue that the spectrum of adversarial attacks on LLMs is much larger than merely…
Compared with transferable untargeted attacks, transferable targeted adversarial attacks could specify the misclassification categories of adversarial samples, posing a greater threat to security-critical tasks. In the meanwhile, 3D…
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,…
Adversarial attacks against computer vision systems have emerged as a critical research area that challenges the fundamental assumptions about neural network robustness and security. This comprehensive survey examines the evolving landscape…
Artificial neural networks in general and deep learning networks in particular established themselves as popular and powerful machine learning algorithms. While the often tremendous sizes of these networks are beneficial when solving…
We investigate if the random feature selection approach proposed in [1] to improve the robustness of forensic detectors to targeted attacks, can be extended to detectors based on deep learning features. In particular, we study the…
With the widespread use of machine learning, concerns over its security and reliability have become prevalent. As such, many have developed defenses to harden neural networks against adversarial examples, imperceptibly perturbed inputs that…
Deep neural networks are vulnerable to adversarial examples (AEs), which have adversarial transferability: AEs generated for the source model can mislead another (target) model's predictions. However, the transferability has not been…
Visual-Language Pre-training (VLP) models have achieved significant performance across various downstream tasks. However, they remain vulnerable to adversarial examples. While prior efforts focus on improving the adversarial transferability…
We analysis performance of semantic segmentation models wrt. adversarial attacks, and observe that the adversarial examples generated from a source model fail to attack the target models. i.e The conventional attack methods, such as PGD and…
Failure cases of black-box deep learning, e.g. adversarial examples, might have severe consequences in healthcare. Yet such failures are mostly studied in the context of real-world images with calibrated attacks. To demystify the…