7 papers
SANAI: Secure ECC Distributed Keyed Parity Embedded in Weights for Protecting Neural Networks against Bit-Flip Attacks
Habibur Rahaman, Daniel Lobo, Md Rezoan Ferdous +1
Quantized neural networks store weights in dense memory, where bit flips caused by voltage scaling, aging, radiation, or deliberate attacks such as RowHammer can severely degrade m…
LEAN: Loss-Engineered Modulation of the Model Weight-Sensitivity Distribution for Efficient, Error-Tolerant Neural Networks
Habibur Rahaman, Swarup Bhunia
The weights of a trained network do not have uniform sensitivity to model accuracy: the 1% most sensitive weights carry about a fifth of the damage a bit flip can do. This distribu…
BARE-AI: Bit-Flip Attack Resilience in AI Hardware through Built-in Performance Monitors
Habibur Rahaman, Swastik Bhattacharya, Sanjay Das +2
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 d…
(A)iSpy: Parasitic Trojans for Machine Learning Infrastructure
Habibur Rahaman, Qipan Xu, Zafaryab Haider +3
Modern machine learning (ML) pipelines depend heavily on third party libraries for graph compilation and hardware acceleration. While current practices audit data and model artifac…
DASH: A Meta-Attack Framework for Synthesizing Effective and Stealthy Adversarial Examples
Abdullah Al Nomaan Nafi, Habibur Rahaman, Zafaryab Haider +4
Numerous techniques have been proposed for generating adversarial examples in white-box settings under strict Lp-norm constraints. However, such norm-bounded examples often fail to…
Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation
Habibur Rahaman, Atri Chatterjee, Swarup Bhunia
Complex neural networks require substantial memory to store a large number of synaptic weights. This work introduces WINGs (Automatic Weight Generator for Secure and Storage-Effici…
Runtime Detection of Adversarial Attacks in AI Accelerators Using Performance Counters
Habibur Rahaman, Atri Chatterjee, Swarup Bhunia
Rapid adoption of AI technologies raises several major security concerns, including the risks of adversarial perturbations, which threaten the confidentiality and integrity of AI a…