Safeguarding Efficacy in Large Language Models: Evaluating Resistance to Human-Written and Algorithmic Adversarial Prompts
"模型防御" 相关文章
Pharmacist: Safety Alignment Data Curation for Large Language Models against Harmful Fine-tuning
Pharmacist: Safety Alignment Data Curation for Large Language Models against Harmful Fine-tuning
Less Diverse, Less Safe: The Indirect But Pervasive Risk of Test-Time Scaling in Large Language Models
Cross-Modal Content Optimization for Steering Web Agent Preferences
Latent Fusion Jailbreak: Blending Harmful and Harmless Representations to Elicit Unsafe LLM Outputs
Anthropic 发现了一种 AI 越狱方法，安全护栏崩塌，文本视觉语音全部沦陷
