57 citations · 62 across the 8 of their papers we have counts for
10 papers
A Deep Dive into Function Inlining and its Security Implications for ML-based Binary Analysis
Omar Abusabha, Jiyong Uhm, Tamer Abuhmed +1
A function inlining optimization is a widely used transformation in modern compilers, which replaces a call site with the callee's body in need. While this transformation improves…
Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack
Eldor Abdukhamidov, Mohammed Abuhamad, Simon S. Woo +2
Vision transformer (ViT) models, when coupled with interpretation models, are regarded as secure and challenging to deceive, making them well-suited for security-critical domains s…
From Attack to Defense: Insights into Deep Learning Security Measures in Black-Box Settings
Firuz Juraev, Mohammed Abuhamad, Eric Chan-Tin +2
Deep Learning (DL) is rapidly maturing to the point that it can be used in safety- and security-crucial applications. However, adversarial samples, which are undetectable to the hu…
Impact of Architectural Modifications on Deep Learning Adversarial Robustness
Firuz Juraev, Mohammed Abuhamad, Simon S. Woo +2
Rapid advancements of deep learning are accelerating adoption in a wide variety of applications, including safety-critical applications such as self-driving vehicles, drones, robot…
Unveiling Vulnerabilities in Interpretable Deep Learning Systems with Query-Efficient Black-box Attacks
Eldor Abdukhamidov, Mohammed Abuhamad, Simon S. Woo +2
Deep learning has been rapidly employed in many applications revolutionizing many industries, but it is known to be vulnerable to adversarial attacks. Such attacks pose a serious t…
Microbial Genetic Algorithm-based Black-box Attack against Interpretable Deep Learning Systems
Eldor Abdukhamidov, Mohammed Abuhamad, Simon S. Woo +2
Deep learning models are susceptible to adversarial samples in white and black-box environments. Although previous studies have shown high attack success rates, coupling DNN models…