Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Aditya Sridhar

Aditya Sridhar

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

ML×1Crypto×1Vision×1

Research Timeline

2026
When Interpretability Becomes a Liability: Adversarial Attacks on CBM Concept Layers

This paper demonstrates that Concept Bottleneck Models (CBMs), despite their interpretability, are highly vulnerable to targeted adversarial attacks that manipulate semantic concepts, and proposes SPECTRA to significantly enhance their robustness.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.CRcs.CVRecentMay 25, 2026

When Interpretability Becomes a Liability: Adversarial Attacks on CBM Concept Layers

Aditya Sridhar

This paper demonstrates that Concept Bottleneck Models (CBMs), despite their interpretability, are highly vulnerable to targeted adversarial attacks that manipulate semantic concepts, and proposes SPE…

View →