Universal and transferable adversarial attacks on aligned language models
Because" out-of-the-box" large language models are capable of generating a great deal of
objectionable content, recent work has focused on aligning these models in an attempt to …
objectionable content, recent work has focused on aligning these models in an attempt to …
Visual adversarial examples jailbreak aligned large language models
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 …
Recently, there has been a surge of interest in integrating vision into Large Language …
Invisible for both camera and lidar: Security of multi-sensor fusion based perception in autonomous driving under physical-world attacks
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 …
various prior studies on its security issues, all of them only consider attacks on camera-or …
Rab: Provable robustness against backdoor attacks
Recent studies have shown that deep neural net-works (DNNs) are vulnerable to
adversarial attacks, including evasion and backdoor (poisoning) attacks. On the defense …
adversarial attacks, including evasion and backdoor (poisoning) attacks. On the defense …
Lot: Layer-wise orthogonal training on improving l2 certified robustness
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 …
are able to enhance adversarial robustness and other model properties such as stability. In …
Visual adversarial examples jailbreak large language models
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 …
Models (LLMs). The proliferation of large Visual Language Models (VLMs), such as …
Smoothmix: Training confidence-calibrated smoothed classifiers for certified robustness
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 …
classifier from neural networks against $\ell_2 $-adversarial perturbations. Under the …
{DiffSmooth}: Certifiably robust learning via diffusion models and local smoothing
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 …
both empirical and certified robustness for a standard model. On the other hand, different …
Trs: Transferability reduced ensemble via promoting gradient diversity and model smoothness
Adversarial Transferability is an intriguing property-adversarial perturbation crafted against
one model is also effective against another model, while these models are from different …
one model is also effective against another model, while these models are from different …
Crop: Certifying robust policies for reinforcement learning through functional smoothing
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 …
safety-critical domains such as autonomous vehicles, a range of empirical studies have …