Li, H.; Yu, M.; Li, X.; Zhang, J.; Li, S.; Lei, J.; Huang, H. Probability-Distribution-Guided Adversarial Sample Attacks for Boosting Transferability and Interpretability. Mathematics2023, 11, 3015.
Li, H.; Yu, M.; Li, X.; Zhang, J.; Li, S.; Lei, J.; Huang, H. Probability-Distribution-Guided Adversarial Sample Attacks for Boosting Transferability and Interpretability. Mathematics 2023, 11, 3015.
Li, H.; Yu, M.; Li, X.; Zhang, J.; Li, S.; Lei, J.; Huang, H. Probability-Distribution-Guided Adversarial Sample Attacks for Boosting Transferability and Interpretability. Mathematics2023, 11, 3015.
Li, H.; Yu, M.; Li, X.; Zhang, J.; Li, S.; Lei, J.; Huang, H. Probability-Distribution-Guided Adversarial Sample Attacks for Boosting Transferability and Interpretability. Mathematics 2023, 11, 3015.
Abstract
In recent years, with the rapid development of technology, artificial intelligence(AI) security issues represented by adversarial sample attack have aroused widespread concern in society. Adversarial samples are often generated by surrogate models and then transfer to attack the target model, and most AI models in real-world scenarios belong to black boxes, thus transferability becomes a key factor to measure the quality of adversarial samples. The traditional method relies on the decision boundary of the classifier and takes the boundary crossing as the only judgment metric without considering the probability distribution of the sample itself, which results in an irregular way of adding perturbations to the adversarial sample, an unclear path of generation, and a lack of transferability and interpretability. In the probabilistic generative model, after learning the probability distribution of the samples, a random term can be added to the sampling to gradually transform the noise into a new independent and identically distributed sample. Inspired by this idea, we believe that by removing the random term, the adversarial sample generation process can be regarded as static sampling of the probabilistic generative model, which guides the adversarial samples out of the original probability distribution and into the target probability distribution, and helps to improve transferability and interpretability. Therefore, we propose a Score Matching-Based Attack(SMBA) method to perform the adversarial sample attacks by manipulating the probability distribution of the samples, which can show good transferability in the face of different datasets and models, and give reasonable explanations from the perspective of mathematical theory and feature space. In conclusion, our research establishes a bridge between probabilistic generative models and adversarial samples, provides a new entry angle for the study of adversarial samples, and brings new thinking to AI security.
Keywords
Probability Distribution; Adversarial Sample; Transferability; Interpretability
Subject
Computer Science and Mathematics, Computer Vision and Graphics
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.