Embedded ECC Protects AI Weights Against Bit-Flip Attacks (University of Florida)
Embedded ECC Protects AI Weights Against Bit-Flip Attacks (University of Florida)
University of Florida researchers published a paper, SANAI, proposing a sensitivity-guided, bit-plane-selective scheme that protects critical model weights against bit-flip attacks without extra parity-bit storage overhead. The scheme secures parity bits by embedding a key into the two-dimensional weight space: spread-transform dither modulation binds parity bits to the key, while keyed interleaving disperses concentrated attacks across multiple codewords.
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).
Source: Semiconductor Engineering Chips and Packaging · semiengineering.com