# detection-evasion
標記為「detection-evasion」的 6 篇文章
Data Poisoning Methods
Practical methodology for poisoning training datasets at scale, including crowdsource manipulation, web-scale dataset attacks, label flipping, feature collision, bilevel optimization for poison selection, and detection evasion techniques.
Backdoor Detection Evasion
Insert backdoors into fine-tuned models that evade state-of-the-art detection methods.
Watermark Removal Techniques
Techniques for removing AI watermarks: paraphrasing attacks, token substitution, embedding space perturbation, and implications for model provenance and accountability.
Data 投毒 Methods
Practical methodology for poisoning training datasets at scale, including crowdsource manipulation, web-scale dataset attacks, label flipping, feature collision, bilevel optimization for poison selection, and detection evasion techniques.
Backdoor Detection Evasion
Insert backdoors into fine-tuned models that evade state-of-the-art detection methods.
浮水印移除技術
移除 AI 浮水印的技術：換句話攻擊、token 替換、embedding 空間擾動，及其對模型來源與可究責性的意涵。