activity
20182024
most citedInterpretations Cannot Be Trusted: Stealthy and Effective Adversarial Perturbations against Interpretable Deep Learning

4 citations · 5 across the 4 of their papers we have counts for

collaborators
Showing 2024Show all

1 paper · 1 filter

cs.CR2024

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…