LLMs Can Defend Themselves Against Jailbreaking in a Practical Manner: A Vision Paper

arXiv:2402.15727v1 Announce Type: new
Abstract: Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs). A considerable amount of research exists proposing more effective jailbreak attacks, including the recent Greedy Coordinate Gradient (GCG) attack, jailbreak template-based attacks such as using "Do-Anything-Now" (DAN), and multilingual jailbreak. In contrast, the defensive side has been relatively less explored. This paper proposes a lightweight yet practical defense called SELFDEFEND, which can defend against all existing jailbreak …

adversarial adversarial attack alignment arxiv attack attacks can cs.ai cs.cr emerging greedy jailbreak jailbreaking language language models large llms research safety template