SoK: Unintended Interactions among Machine Learning Defenses and Risks
CoRR(2023)
摘要
Machine learning (ML) models cannot neglect risks to security, privacy, and
fairness. Several defenses have been proposed to mitigate such risks. When a
defense is effective in mitigating one risk, it may correspond to increased or
decreased susceptibility to other risks. Existing research lacks an effective
framework to recognize and explain these unintended interactions. We present
such a framework, based on the conjecture that overfitting and memorization
underlie unintended interactions. We survey existing literature on unintended
interactions, accommodating them within our framework. We use our framework to
conjecture on two previously unexplored interactions, and empirically validate
our conjectures.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要