Detecting Trojaned DNNs via Spectral Regression Analysis

Computer Science > Cryptography and Security [Submitted on 20 May 2026] Detecting Trojaned DNNs via Spectral Regression Analysis Samuele Pasini, Jinhan Kim, Paolo Tonella Modern DNNs are repeatedly fine-tuned to incorporate new data and functionality. This evolutionary workflow introduces a security risk when updated data cannot be fully trusted, as adversaries may implant Trojans during fine-tuning. We present MIST, a Trojan detection approach that analyzes how a model's internal representations change during fine-tuning. Rather than attempting to reconstruct trigger conditions, MIST characterizes benign model evolution using pre-activation spectra and flags updates whose spectral deviations are inconsistent with this reference. This framing treats Trojan detection as a regression problem over model updates. An empirical evaluation across four datasets and eight Trojan attacks shows that spectral distances reliably distinguish Trojaned updates from clean fine-tuning. MIST outperforms state-of-the-art detection accuracy after a single update, without requiring any knowledge about the poisoned data or the trigger, and remains effective under multi-step benign evolution, with graceful and bounded degradation. These results indicate that spectral evolution provides a stable and assumption-light signal for detecting malicious model updates. Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Software Engineering (cs.SE) Cite as: arXiv:2605.21146 [cs.CR]   (or arXiv:2605.21146v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2605.21146 Focus to learn more Submission history From: Samuele Pasini Mr [view email] [v1] Wed, 20 May 2026 13:19:27 UTC (1,183 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-05 Change to browse by: cs cs.AI cs.SE References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)