Despite efforts to align large language models (LLMs) with human values, widely-used
LLMs such as GPT, Llama, Claude, and PaLM are susceptible to jailbreaking 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 …

Designing neural networks with bounded Lipschitz constant is a promising way to obtain
certifiably robust classifiers against adversarial examples. However, the relevant progress …

Great advances in deep neural networks (DNNs) have led to state-of-the-art performance on
a wide range of tasks. However, recent studies have shown that DNNs are vulnerable to …

To obtain, deterministic guarantees of adversarial robustness, specialized training methods
are used. We propose, SABR, a novel such certified training method, based on the key …

Adversarial poisoning attacks distort training data in order to corrupt the test-time behavior of
a classifier. A provable defense provides a certificate for each test sample, which is a lower …

Recent studies have shown that deep neural net-works (DNNs) are vulnerable to
adversarial attacks, including evasion and backdoor (poisoning) attacks. On the defense …

Certified patch defenses can guarantee robustness of an image classifier to arbitrary
changes within a bounded contiguous region. But, currently, this robustness comes at a cost …

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 …

The right to be forgotten calls for efficient machine unlearning techniques that make trained
machine learning models forget a cohort of data. The combination of training and unlearning …