From Attack to Defense: Insights into Deep Learning Security Measures in Black-Box Settings
Document Type
Conference Proceeding
Publication Date
5-2024
Publication Title
2024 Silicon Valley Cybersecurity Conference
Abstract
Deep Learning (DL) is rapidly maturing to the point that it can be used in safety- and security crucial applications, such as self-driving vehicles, surveillance, drones, and robots. However, adversarial samples, which are undetectable to the human eye, pose a serious threat that can cause the model to misbehave and compromise the performance of such applications. Addressing the robustness of DL models has become crucial to understanding and defending against adversarial attacks. In this study, we perform comprehensive experiments to examine the effect of adversarial attacks and defenses on various model architectures across well-known datasets. Our research focuses on black-box attacks such as SimBA, HopSkipJump, MGAAttack, and boundary attacks, as well as preprocessor-based defensive mechanisms, including bits squeezing, median smoothing, and JPEG filter. Experimenting with various models, our results demonstrate that the level of noise needed for the attack increases as the number of layers increases. Moreover, the attack success rate decreases as the number of layers increases. This indicates that model complexity and robustness have a significant relationship. Investigating the diversity and robustness relationship, our experiments with diverse models show that having a large number of parameters does not imply higher robustness. Our experiments extend to show the effects of the training dataset on model robustness. Using various datasets such as ImageNet-1000, CIFAR-100, and CIFAR-10 are used to evaluate the black-box attacks. Considering the multiple dimensions of our analysis, e.g., model complexity and training dataset, we examined the behavior of black-box attacks when models apply defenses. Our results show that applying defense strategies can significantly reduce attack effectiveness. This research provides in-depth analysis and insight into the robustness of DL models against various attacks, and defenses
Identifier
arxiv:2405.01963
Recommended Citation
Juraev, F., Abuhamad, M., Chan-Tin, E., Thiruvathukal, G.K., & Abuhmed, T. (2024). From Attack to Defense: Insights into Deep Learning Security Measures in Black-Box Settings, In Proceedings of the 2024 Silicon Valley Cybersecurity Conference (SVCC).
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
