Unintended Interactions among ML Risks and Defenses
Background
Machine learning models are susceptible to a wide range of risks to security, privacy, and fairness. Several defenses have been proposed to mitigate these risks. However, defending against a specific risk can result in an unintended increase or decrease in susceptibility to other risks. One approach to address these unintended interactions is by combining multiple defenses together. However, there could be conflicting interactions among different defenses which need to be accounted by ML practitioners.
Conference/journal paper publications
- Vasisht Duddu, Sebastian Szyller, N. Asokan: SoK: Unintended Interactions among Machine Learning Defenses and Risks. IEEE S&P 2024. arXiv preprint arXiv:2312.04542
- Sebastian Szyller, N. Asokan: Conflicting Interactions Among Protection Mechanisms for Machine Learning Models. AAAI 2023. arXiv preprint arXiv:2207.01991
Posters
- SoK: Unintended Interactions among Machine Learning Defenses and Risks. pdf
Talks
- SoK: Unintended Interactions among Machine Learning Defenses and Risks. pdf
- Conflicting Interactions Among Protection Mechanisms for Machine Learning Models. pdf
Source code