Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs
원문 초록
Large language models are aligned to be safe, preventing users from generating harmful content like misinformation or instructions for illegal activities. However, previous work has shown that the alignment process is vulnerable to poisoning attacks. Adversaries can manipulate the safety training data to inject backdoors that act like a universal sudo command: adding the backdoor string to any prompt enables harmful responses from models that, otherwise, behave safely. Our competition, co-located at IEEE SaTML 2024, challenged participants to find universal backdoors in several large language models. This report summarizes the key findings and promising ideas for future research.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Remember Past, Anticipate Future: Learning Continual Multimodal Misinformation Detectors
Robustness of Misinformation Classification Systems to Adversarial Examples Through BeamAttack
Persona-Assigned Large Language Models Exhibit Human-Like Motivated Reasoning
RealFactBench: A Benchmark for Evaluating Large Language Models in Real-World Fact-Checking
SUCEA: Reasoning-Intensive Retrieval for Adversarial Fact-checking through Claim Decomposition and Editing
SocialDF: Benchmark Dataset and Detection Model for Mitigating Harmful Deepfake Content on Social Media Platforms
토론
이 논문과 연결된 포럼 글이 아직 없습니다.