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

Jinhan Kim

1 indexed paper

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

Publications per year

1
26

Top categories

Crypto×1AI×1Software Eng.×1

Frequent co-authors

Samuele Pasini1×
Paolo Tonella1×

Research Timeline

2026
Detecting Trojaned DNNs via Spectral Regression Analysis

The paper introduces MIST, a novel Trojan detection method that analyzes the spectral changes in a DNN's internal representations during fine-tuning to reliably identify malicious model updates.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIcs.SERecentMay 20, 2026

Detecting Trojaned DNNs via Spectral Regression Analysis

Samuele Pasini, Jinhan Kim, Paolo Tonella

The paper introduces MIST, a novel Trojan detection method that analyzes the spectral changes in a DNN's internal representations during fine-tuning to reliably identify malicious model updates.

View →