片上监控器检测 AI 加速器中的比特翻转攻击（UF、UT Dallas、RPI）

On-Chip Monitors Detect Bit-Flip Attacks in AI Accelerators (UF, UT Dallas, RPI)

AI 导读

佛罗里达大学、得克萨斯大学达拉斯分校与伦斯勒理工学院的研究团队发表论文 BARE-AI，提出一种在 AI 推理时检测、定位并缓解比特翻转攻击（BFA）的运行时框架。该方案利用内置性能监控器保护深度神经网络，避免现有防御硬件开销大、依赖重训练或难以应对定向翻转的问题。

正文 · 原文

popularity

Researchers at the University of Florida, University of Texas at Dallas, and Rensselaer Polytechnic Institute published a technical paper titled “BARE-AI: Bit-Flip Attack Resilience in AI Hardware through Built-in Performance Monitors.”

Abstract Excerpt:

“Deep Neural Networks (DNNs) are integral to many safety critical systems, yet they remain highly vulnerable to bit-flip attacks (BFAs), where a few memory level perturbations can drastically degrade accuracy. Existing defenses incur significant hardware overhead, depend on retraining, or fail against targeted flips. We propose BARE-AI, a runtime framework that detects, localizes, and mitigates BFAs during AI inference.”

Find the technical paper here. October 2026.

Rahaman, Habibur, Swastik Bhattacharya, Sanjay Das, Kanad Basu, and Swarup Bhunia. “BARE-AI: Bit-Flip Attack Resilience in AI Hardware through Built-in Performance Monitors.” arXiv preprint arXiv:2610.08739 (2026).