Metraipolis › archive › dc_ebd91102b507
BARE-AI: Bit-Flip Attack Resilience in AI Hardware through Built-in Performance Monitors — arXiv:2610.08739
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.08739
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:35:20.389Z
- SHA-256 of the archived text
145b2f9b82b223f4d5ed3a74dec17fbe30ad3ddf35101bdf9a5a50b5f2a1d81a- Stable URL of this page
https://metraipolis.com/documento/dc_ebd91102b507
How to cite
BARE-AI: Bit-Flip Attack Resilience in AI Hardware through Built-in Performance Monitors — arXiv:2610.08739 — arXiv (en), https://arxiv.org/abs/2610.08739 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ebd91102b507 (Metraipolis archive dc_ebd91102b507, sha256 145b2f9b82b223f4d5ed3a74dec17fbe30ad3ddf35101bdf9a5a50b5f2a1d81a)
BibTeX
@misc{dcebd91102b507,
title = {BARE-AI: Bit-Flip Attack Resilience in AI Hardware through Built-in Performance Monitors — arXiv:2610.08739},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.08739},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ebd91102b507; sha256 145b2f9b82b223f4d5ed3a74dec17fbe30ad3ddf35101bdf9a5a50b5f2a1d81a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08739. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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 inference. BARE-AI introduces AI Performance Counters (APCs), lightweight hardware monitors in the accelerator datapath that capture per-layer activation statistics such as sparsity, entropy, kurtosis, and spectral shift. These are analyzed by the Predictive Unit for Layer Security Evaluation (PULSE), a compact detector trained offline as an ensemble of classifiers and realized on-chip as a small neural engine. For explainability and recovery, BARE-AI introduces an Activation Shift Index (ASI) for layer level fault localization and a z-score based repair that resets anomalous weights toward clean layer statistics. Across CNNs, Vision Transformers, and Large Language Models under random, targeted, adaptive, and magnitude based BFAs, BARE-AI achieves up to 98% detection accuracy on vision models and 74% to 95% on language models, restores near clean accuracy for CNNs and ViTs, and provides partial recovery for LLMs. Synthesized at 28nm, the monitoring infrastructure incurs under 3% energy, under 4% area, and about 10% latency overhead, with a configurable operating point that reduces latency overhead to about 6%. Unlike error correcting codes, whose redundancy grows with the number of tolerated flips, BARE-AI's overhead remains constant regardless of attack strength, making it attractive for resource constrained, safety critical edge applications such as autonomous systems, energy, and healthcare. Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno). Categorie arXiv: Cryptography and Security (cs.CR). Pagina del lavoro: https://arxiv.org/abs/2610.08739 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T11:18:39.703Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).