SoK: Unintended Interactions among Machine Learning Defenses and Risks

December 07, 2023 Β· Declared Dead Β· πŸ› IEEE Symposium on Security and Privacy

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Vasisht Duddu, Sebastian Szyller, N. Asokan arXiv ID 2312.04542 Category cs.CR: Cryptography & Security Cross-listed cs.LG Citations 6 Venue IEEE Symposium on Security and Privacy Last Checked 3 months ago
Abstract
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.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Cryptography & Security

Died the same way β€” πŸ‘» Ghosted