佛罗里达大学提出 SANAI：嵌入式 ECC 保护神经网络权重免受位翻转攻击
Embedded ECC Protects AI Weights Against Bit-Flip Attacks (University of Florida)
佛罗里达大学研究人员发表论文 SANAI，提出一种基于敏感度引导、按位平面选择的方案，保护关键模型权重免受位翻转攻击，且不产生额外的校验位存储开销。该方案通过密钥嵌入二维权重空间保证校验位安全：spread-transform dither modulation 将校验位绑定到密钥，keyed interleaving 则将集中式攻击分散到多个码字中。
Researchers at the University of Florida published “SANAI: Secure ECC Distributed Keyed Parity Embedded in Weights for Protecting Neural Networks against Bit-Flip Attacks.”
Abstract Excerpt:
“We propose SANAI, a sensitivity-guided, bit-plane-selective scheme that protects critical model weights against bit flips with zero additional parity-storage overhead. SANAI secures parity through keyed embedding across a two-dimensional weight space: spread-transform dither modulation binds parity to a secret key, and keyed interleaving disperses concentrated attacks across codewords.”
Find the technical paper here. November 2026
Rahaman, Habibur, Daniel Lobo, Md Rezoan Ferdous, and Swarup Bhunia. “SANAI: Secure ECC Distributed Keyed Parity Embedded in Weights for Protecting Neural Networks against Bit-Flip Attacks.” arXiv preprint arXiv:2611.02042 (2026).
来源： Semiconductor Engineering 芯片与封装 · semiengineering.com