Pith. sign in

REVIEW

SoK: Unintended Interactions among Machine Learning Defenses and Risks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2312.04542 v2 pith:3YV4INB5 submitted 2023-12-07 cs.CR cs.LG

SoK: Unintended Interactions among Machine Learning Defenses and Risks

classification cs.CR cs.LG
keywords interactionsframeworkrisksunintendedconjecturedefenseseffectiveexisting
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original 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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.