9 papers
Faults That Fortify: CNN Adversarial Robustness via GPU Undervolting
Behnam Omidi, Ahmad Tahmasivand, Husam Alsyouri +4
Convolutional Neural Networks (CNNs) face a dual challenge: vulnerability to adversarial attacks and prohibitive training cost. Adversarial training is effective but expensive, a b…
Privacy in Federated Learning with Spiking Neural Networks
Dogukan Aksu, Jesus Martinez del Rincon, Ihsen Alouani
Spiking neural networks (SNNs) have emerged as prominent candidates for embedded and edge AI. Their inherent low power consumption makes them far more efficient than conventional A…
Stealth by Conformity: Evading Robust Aggregation through Adaptive Poisoning
Ryan McGaughey, Jesus Martinez del Rincon, Ihsen Alouani
Federated Learning (FL) is a distributed learning paradigm designed to address privacy concerns. However, FL is vulnerable to poisoning attacks, where Byzantine clients compromise…
Poison Once, Refuse Forever: Weaponizing Alignment for Injecting Bias in LLMs
Md Abdullah Al Mamun, Ihsen Alouani, Nael Abu-Ghazaleh
Large Language Models (LLMs) are aligned to meet ethical standards and safety requirements by training them to refuse answering harmful or unsafe prompts. In this paper, we demonst…
On Jailbreaking Quantized Language Models Through Fault Injection Attacks
Noureldin Zahran, Ahmad Tahmasivand, Ihsen Alouani +2
The safety alignment of Language Models (LMs) is a critical concern, yet their integrity can be challenged by direct parameter manipulation attacks, such as those potentially induc…
SnatchML: Hijacking ML models without Training Access
Mahmoud Ghorbel, Halima Bouzidi, Ioan Marius Bilasco +1
Model hijacking can cause significant accountability and security risks since the owner of a hijacked model can be framed for having their model offer illegal or unethical services…