Universal Jailbreak Suffixes Are Strong Attention Hijackers

We study suffix-based jailbreaks$\unicodex2013$a powerful family of attacks against large language models LLMs that optimize adversarial suffixes to circumvent safety alignment. Focusing on the widely used foundational GCG attack Zou et al., 2023, we observe that suffixes vary in efficacy: some...

AudioJailbreak: Jailbreak Attacks against End-To-End Large Audio-Language Models

Jailbreak attacks to Large audio-language models LALMs are studied recently, but they achieve suboptimal effectiveness, applicability, and practicability, particularly, assuming that the adversary can fully manipulate user prompts. In this work, we first conduct an extensive experiment showing th...

Measuring Computational Universality of Fully Homomorphic Encryption

Many real-world applications, such as machine learning and graph analytics, involve combinations of linear and non-linear operations. As these applications increasingly handle sensitive data, there is a significant demand for privacy-preserving computation techniques capable of efficiently...