Warning: this paper contains data, prompts, and model outputs that are offensive in nature. Recently, there has been a surge of interest in integrating vision into Large Language …
In Autonomous Driving (AD) systems, perception is both security and safety critical. Despite various prior studies on its security issues, all of them only consider attacks on camera-or …
Recent studies have shown that deep neural net-works (DNNs) are vulnerable to adversarial attacks, including evasion and backdoor (poisoning) attacks. On the defense …
X Xu, L Li, B Li - Advances in Neural Information Processing …, 2022 - proceedings.neurips.cc
Recent studies show that training deep neural networks (DNNs) with Lipschitz constraints are able to enhance adversarial robustness and other model properties such as stability. In …
Recently, there has been a surge of interest in introducing vision into Large Language Models (LLMs). The proliferation of large Visual Language Models (VLMs), such as …
Randomized smoothing is currently a state-of-the-art method to construct a certifiably robust classifier from neural networks against $\ell_2 $-adversarial perturbations. Under the …
Diffusion models have been leveraged to perform adversarial purification and thus provide both empirical and certified robustness for a standard model. On the other hand, different …
Z Yang, L Li, X Xu, S Zuo, Q Chen… - Advances in …, 2021 - proceedings.neurips.cc
Adversarial Transferability is an intriguing property-adversarial perturbation crafted against one model is also effective against another model, while these models are from different …
As reinforcement learning (RL) has achieved great success and been even adopted in safety-critical domains such as autonomous vehicles, a range of empirical studies have …