BARE-AI: Bit-Flip Attack Resilience in AI Hardware through Built-in Performance Monitors
cs.CR
Submitted: 2026-10-06
Updated: 2026-10-07
Sources
- Impactful Bit-Flip Search on Full-precision Models
- Performance Assessment of Linear Models of Hydropower Plants
- (A)iSpy: Parasitic Trojans for Machine Learning Infrastructure
- A survey on hardware-based malware detection approaches
- Aegis: Mitigating Targeted Bit-flip Attacks against Deep Neural Networks
- LLaMA: Open and Efficient Foundation Language Models
- Measuring Massive Multitask Language Understanding
- Maximal Brain Damage Without Data or Optimization: Disrupting Neural Networks via Sign-Bit Flips
- DNN-Defender: A Victim-Focused In-DRAM Defense Mechanism for Taming Adversarial Weight Attack on DNNs
- DeepNcode: Encoding-Based Protection against Bit-Flip Attacks on Neural Networks
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs