Embedded ECC Protects AI Weights Against Bit-Flip Attacks (University of Florida)

<p>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: &#8220;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... <a class="read_more" href="https://semiengineering.com/embedded-ecc-protects-ai-weights-against-bit-flip-attacks-university-of-florida/">&#187; read more</a></p> <p>The post <a href="https://semiengineering.com/embedded-ecc-protects-ai-weights-against-bit-flip-attacks-university-of-florida/">Embedded ECC Protects AI Weights Against Bit-Flip Attacks (University of Florida)</a> appeared first on <a href="https://semiengineering.com">Semiconductor Engineering</a>.</p>