SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding

arXiv:2402.08983v1 Announce Type: new
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 …

applications arxiv assistance attacks aware chatbot code cs.ai cs.cr decoding defending human human values jailbreak language language models large llm llms real safety world