How stealthy is stealthy? Studying the Efficacy of Black-Box Adversarial Attacks in the Real World
Not on the map. Why?
Abstract (arXiv)
Deep learning systems, critical in domains like autonomous vehicles, are vulnerable to adversarial examples (crafted inputs designed to mislead classifiers). This study investigates black-box adversarial attacks in computer vision. This is a realistic scenario, where attackers have query-only access to the target model. Three properties are introduced to evaluate attack feasibility: robustness to compression, stealthiness to automatic detection, and stealthiness to human inspection. State-of-the-Art methods tend to prioritize one criterion at the expense of others. We propose ECLIPSE, a novel attack method employing Gaussian blurring on sampled gradients and a local surrogate model. Comprehensive experiments on a public dataset highlight ECLIPSE's advantages, demonstrating its contribution to the trade-off between the three properties.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 27 of its 38 references that are in the map. First posted on arXiv 3 Jun 2025.
Builds on
27 of 38 references.
References · 27
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
- 2013Intriguing properties of neural networkscited by 5,155
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
- 2016Adversarial examples in the physical worldcited by 1,769
- 2016Practical Black-Box Attacks against Machine Learningcited by 903
- 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
- 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 666
- 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 536
- 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 462
- 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 446
- 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 333
15 more
- 2019Simple Black-box Adversarial Attackscited by 251
- 2020QEBA: Query-Efficient Boundary-Based Blackbox Attackcited by 104
- 2018Local Gradients Smoothing: Defense against localized adversarial attackscited by 87
- 2020Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attackscited by 65
- 2020SurFree: a fast surrogate-free black-box attackcited by 60
- 2020Perturbing Across the Feature Hierarchy to Improve Standard and Strict Blackbox Attack Transferabilitycited by 57
- 2019Stateful Detection of Black-Box Adversarial Attackscited by 56
- 2021Adversarial Example Detection for DNN Models: A Review and Experimental Comparisoncited by 52
- 2020Blacklight: Scalable Defense for Neural Networks against Query-Based Black-Box Attackscited by 37
- 2021On the Effectiveness of Small Input Noise for Defending Against Query-based Black-Box Attackscited by 17
- 2022Object Detection in Autonomous Vehicles: Status and Open Challengescited by 14
- 2023Stateful Defenses for Machine Learning Models Are Not Yet Secure Against Black-box Attackscited by 11
- 2017Evading Classifiers by Morphing in the Darkcited by 9
- 2022Adversarial Scratches: Deployable Attacks to CNN Classifierscited by 5
- 2022Hide and Seek: on the Stealthiness of Attacks against Deep Learning Systemscited by 3
Built on by
Citing papers per year: 2026: 1.
1 paper.