最近一年的 AI 安全论文
本站共收录 51 篇- AngelFingerprint：一种面向文本引导图像编辑的可追溯、可解释且白盒隐蔽水印
AngelFingerprint: A Traceable, Explainable, and White-Box Stealthy Watermark for Text-Guided Image Editing
- HRGuard：拦截多轮 Agent 对话中的关系操纵
HRGuard: Gating Relationship Manipulation in Multi-Turn Agentic AI Conversations
- 鲁棒性优化防御存在共享漏洞，突破一个即可暴露整个防御家族
Shared Vulnerabilities in Robustness-Optimized Defenses: One Breach Exposes the Family
- 标签效应：人类与 LLM 评委在信任评估中共享启发式依赖
Label Effects: Shared Heuristic Reliance in Trust Assessment by Humans and LLM-as-a-Judge
- 超越标准基准：系统审计视觉语言模型跨多样任务对自然语义变化的鲁棒性
Beyond Standard Benchmarks: A Systematic Audit of Vision-Language Model's Robustness to Natural Semantic Variation Across Diverse Tasks
- EvoGuard：面向实用且持续演进的 AI 生成图像检测的可扩展智能体强化学习框架
EvoGuard: An Extensible Agentic RL-based Framework for Practical and Evolving AI-Generated Image Detection
- SGM：通过神经元级去毒为多模态大语言模型提供“安全眼镜”
SGM: Safety Glasses for Multimodal Large Language Models via Neuron-Level Detoxification
- GFT-GCN：结合谱扩散的隐私保护 3D 人脸网格识别
GFT-GCN: Privacy-Preserving 3D Face Mesh Recognition with Spectral Diffusion
署名以 dblp 和本人的 Google Scholar 为准；只列本站收录的 AI 安全论文。