HackerPapers

arXiv:2301.10407cs.SE

Don't Lie to Me: Avoiding Malicious Explanations with STEALTH

Lauren Alvarez, Tim Menzies

HN submission. Found in a submission link or body. Submitters do not count as commenters in the main ranking; a submission is not an endorsement.

Abstract

STEALTH is a method for using some AI-generated model, without suffering from malicious attacks (i.e. lying) or associated unfairness issues. After recursively bi-clustering the data, STEALTH system asks the AI model a limited number of queries about class labels. STEALTH asks so few queries (1 per data cluster) that malicious algorithms (a) cannot detect its operation, nor (b) know when to lie.

arXiv comments
6 pages, 6 Tables, 3 figures
Journal reference
DOI
Subjects
cs.SESoftware Engineering cs.AIArtificial Intelligence cs.CRCryptography and Security

On Hacker News

No comments linking this paper were found in the collected sources. Found in 1 HN submission from Jan 2023 to Jan 2023. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments0 threads

No comments linking this paper were found in the collected sources. Open submission discussions.

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.