Unmasking the Vulnerabilities of Deep Learning Models: A Multi-Dimensional Analysis of Adversarial Attacks and Defenses

  • Firuz Juraev
  • , Mohammed Abuhamad
  • , Eric Chan-Tin
  • , George K. Thiruvathukal
  • , Tamer Abuhmed

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

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.

Original languageEnglish
Title of host publication2024 Silicon Valley Cybersecurity Conference, SVCC 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350383140
DOIs
StatePublished - 2024
Event2024 Silicon Valley Cybersecurity Conference, SVCC 2024 - Seoul, Korea, Republic of
Duration: 17 Jun 202419 Jun 2024

Publication series

Name2024 Silicon Valley Cybersecurity Conference, SVCC 2024

Conference

Conference2024 Silicon Valley Cybersecurity Conference, SVCC 2024
Country/TerritoryKorea, Republic of
CitySeoul
Period17/06/2419/06/24

Keywords

  • Adversarial Perturbations
  • Black-box Attacks
  • Deep Learning
  • Defensive Techniques
  • Threat Analysis

Fingerprint

Dive into the research topics of 'Unmasking the Vulnerabilities of Deep Learning Models: A Multi-Dimensional Analysis of Adversarial Attacks and Defenses'. Together they form a unique fingerprint.

Cite this