PulseAugur
实时 13:46:46

New MIST method detects Trojans in fine-tuned DNNs

Researchers have developed a new method called MIST to detect malicious Trojans embedded in deep neural networks (DNNs) during the fine-tuning process. MIST analyzes the spectral changes in a model's internal representations to identify deviations indicative of a Trojan attack. This approach treats Trojan detection as a regression problem and has demonstrated superior accuracy compared to existing methods, even without prior knowledge of the attack's specifics. AI

影响 Introduces a novel technique for enhancing the security of AI models against sophisticated attacks during development.

排序理由 Academic paper detailing a new method for detecting security vulnerabilities in AI models.

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

New MIST method detects Trojans in fine-tuned DNNs

报道来源 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Samuele Pasini, Jinhan Kim, Paolo Tonella ·

    Detecting Trojaned DNNs via Spectral Regression Analysis

    arXiv:2605.21146v1 Announce Type: cross Abstract: 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-tunin…

  2. arXiv cs.AI TIER_1 English(EN) · Paolo Tonella ·

    Detecting Trojaned DNNs via Spectral Regression Analysis

    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 th…