最近一年的 AI 安全论文
本站共收录 25 篇- inLoRA-MINT：用内部表示审计领域适配 LLM 的训练数据
inLoRA-MINT: Internal Representations for Auditing Training Data in Domain-adapted LLMs
- FakeIDet3-DB：面向证件安全评测的数字攻击精修与图像块提取
FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking
- AIriskEval-edu Demo：审计教学讲解中的教学风险
AIriskEval-edu Demo: Auditing of Pedagogical Risks in Educational Explanations
- AI Act 及更广监管框架下智能系统风险评估与管理综述
Overview of Risk Assessment and Management for Intelligent Systems under the AI Act and Beyond
- AIriskEval-edu：用于评估 AI 介导 K-12 教学讲解风险的新数据集
AIriskEval-edu: New Dataset for Risk Assessment in AI-mediated K-12 Educational Explanations
- 用生物特征与博弈实验评估 AI 交互中的社会工程风险
Evaluating Social Engineering Risks in AI-based Interaction using Biometrics and a Gaming Setup
- AVAPrintDB：面向头像指纹识别的多生成器逼真说话头像公开数据库与基准
Leveraging Avatar Fingerprinting: A Multi-Generator Photorealistic Talking-Head Public Database and Benchmark
- EduEVAL-DB：面向教育解释教学风险评估的基于角色数据集
EduEVAL-DB: A Role-Based Dataset for Pedagogical Risk Evaluation in Educational Explanations
署名以 dblp 和本人的 Google Scholar 为准；只列本站收录的 AI 安全论文。