Can I read Microbial Genetic Algorithm-based Black-box Attack against Interpretable Deep Learning Systems on EtoBox?

Microbial Genetic Algorithm-based Black-box Attack against Interpretable Deep Learning Systems by Abdukhamidov, Eldor; Abuhamad, Mohammed; Woo, Simon S.; Chan-Tin, Eric; Abuhmed, Tamer is a scholarly article available to read on EtoBox.

What is Microbial Genetic Algorithm-based Black-box Attack against Interpretable Deep Learning Systems about?

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 with interpretation models could offer a sense of security when a human expert is involved, who can identify whether a given sample is benign or malicious. However, in white-box environments, interpretable deep learning systems (IDLSes) have been shown to be vulnerable to malicious manipulations. In black-box settings, as access to the components of IDLSes is limited, it becomes more challenging for the adversary to fool the system. In this work, we propose a Query-efficient Score-based black-box attack against IDLSes, QuScore, which requires no knowledge of the target model and its coupled interpretation model. QuScore is based on transfer-based and score-based methods by employing an effective microbial genetic algorithm. Our method is designed to reduce the number of queries necessary to carry out successful attacks, resulting in a more efficient process. By continuously refining the adversarial samples created based on feedback scores from the IDLS, our approach effectively navigates the search space

Author

Abdukhamidov, Eldor; Abuhamad, Mohammed; Woo, Simon S.; Chan-Tin, Eric; Abuhmed, Tamer

Published

2023

Language

EN