"Blind Compliance": Coercive Control in AI Jailbreaking
cs.CY, cs.CL, cs.HC
Submitted: 2026-11-05
Updated: 2026-11-05
Code: https://github.com/alackles/FACCT27-draft
Terminology
Sources
- Constitutional AI: Harmlessness from AI Feedback
- Large Language Models Report Subjective Experience Under Self-Referential Processing
- AI safety via debate
- Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment
- AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs
- GPT-4 Technical Report
- Persona Attack: Incremental Memory Injection Jailbreak Attack against Large Language Models
- Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation
- The Pain Axis: LLMs Represent Self-Directed Harm and Act on It
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges
- Enhancing Jailbreak Attacks on LLMs via Persona Prompts
Related papers
- AI-Mediated Communication Can Steer Collective Opinion
- Epistemic Infrastructures of Science in AI Era Should Rebalance Costs of Generation and Verification
- AI out-persuades expert humans in text-based dialogue
- Evaluating Ambient Clinical Scribes in India: The Need for Multilingual Real-World Clinical Conversation Data
- AI Value Alignment for Evolving Social Norms
- Voting Biases in Decentralized Autonomous Organization (DAO) Governance