SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding

arXiv:2402.08983v1 Announce Type: cross
Abstract: As large language models (LLMs) become increasingly integrated into real-world applications such as code generation and chatbot assistance, extensive efforts have been made to align LLM behavior with human values, including safety. Jailbreak attacks, aiming to provoke unintended and unsafe behaviors from LLMs, remain a significant/leading LLM safety threat. In this paper, we aim to defend LLMs against jailbreak attacks by introducing SafeDecoding, a safety-aware decoding strategy for LLMs to generate helpful and harmless responses …

abstract applications arxiv attacks become behavior chatbot code code generation cs.ai cs.cl cs.cr decoding human jailbreak language language models large language large language models llm llms safety type values via world