计算机科学
稳健性(进化)
探测器
实时计算
计算机安全
人工智能
计算机视觉
语音识别
噪音(视频)
数据丢失
毒物控制
工程类
数据收集
作者
Ian J. Miller,Ke Li,Dan Lin
出处
期刊:
日期:2025-11-11
卷期号:: 158-165
被引量:1
标识
DOI:10.1109/cic67133.2025.00027
摘要
The rise of generative AI in fabricating or altering audio poses a significant risk to public confidence in what has traditionally been a reliable medium, amplifying the spread of synthetic content to an unprecedented degree. Safeguarding the integrity of media requires research dedicated to developing dependable methods for differentiating between authentic and AI-generated content. When combined with legislative measures that drive adoption on social platforms, these detection systems could help mitigate this concerning threat. This project focuses on strengthening such detectors against a specific challenge they may encounter in real-world deployment: data poisoning attacks. Our defense mechanism called Feature Inspection and Learning for Threat Examination and Removal (FILTER), is robust against two common types of data poisoning attacks: targeted label flipping attacks. and backdoor attacks.
科研通智能强力驱动
Strongly Powered by AbleSci AI