5 papers
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…
LASH: Adaptive Semantic Hybridization for Black-Box Jailbreaking of Large Language Models
Abdullah Al Nomaan Nafi, Fnu Suya, Swarup Bhunia +1
Jailbreak attacks expose a persistent gap between the intended safety behavior of aligned large language models and their behavior under adversarial prompting. Existing automated m…
POLARIS: Explainable Artificial Intelligence for Mitigating Power Side-Channel Leakage
Tanzim Mahfuz, Sudipta Paria, Tasneem Suha +2
Microelectronic systems are widely used in many sensitive applications (e.g., manufacturing, energy, defense). These systems increasingly handle sensitive data (e.g., encryption ke…
SALTY: Explainable Artificial Intelligence Guided Structural Analysis for Hardware Trojan Detection
Tanzim Mahfuz, Pravin Gaikwad, Tasneem Suha +2
Hardware Trojans are malicious modifications in digital designs that can be inserted by untrusted supply chain entities. Hardware Trojans can give rise to diverse attack vectors su…
X-DFS: Explainable Artificial Intelligence Guided Design-for-Security Solution Space Exploration
Tanzim Mahfuz, Swarup Bhunia, Prabuddha Chakraborty
Design and manufacturing of integrated circuits predominantly use a globally distributed semiconductor supply chain involving diverse entities. The modern semiconductor supply chai…