mlsanityData to 14 Oct 2026

Physical Adversarial Attacks For Camera-based Smart Systems: Current Trends, Categorization, Applications, Research Challenges, and Future Outlook

arXiv 2308.06173 ↗First posted 11 Aug 2023cs.CR cs.AI cs.CVcited by 20

Not on the map. Why?

Abstract (arXiv)

In this paper, we present a comprehensive survey of the current trends focusing specifically on physical adversarial attacks. We aim to provide a thorough understanding of the concept of physical adversarial attacks, analyzing their key characteristics and distinguishing features. Furthermore, we explore the specific requirements and challenges associated with executing attacks in the physical world. Our article delves into various physical adversarial attack methods, categorized according to their target tasks in different applications, including classification, detection, face recognition, semantic segmentation and depth estimation. We assess the performance of these attack methods in terms of their effectiveness, stealthiness, and robustness. We examine how each technique strives to ensure the successful manipulation of DNNs while mitigating the risk of detection and withstanding real-world distortions. Lastly, we discuss the current challenges and outline potential future research directions in the field of physical adversarial attacks. We highlight the need for enhanced defense mechanisms, the exploration of novel attack strategies, the evaluation of attacks in different application domains, and the establishment of standardized benchmarks and evaluation criteria for physical adversarial attacks. Through this comprehensive survey, we aim to provide a valuable resource for researchers, practitioners, and policymakers to gain a holistic understanding of physical adversarial attacks in computer vision and facilitate the development of robust and secure DNN-based systems.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Builds on 132 of its 191 references that are in the map. First posted on arXiv 11 Aug 2023.

Builds on

132 of 191 references.

References · 132

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2017Mask R-CNNcited by 7,277
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  6. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  7. 2022Generative Adversarial Networkscited by 5,627
  8. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  9. 2013Intriguing properties of neural networkscited by 5,155
  10. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  11. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  12. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
38 more
  1. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  2. 2015Fast R-CNNcited by 2,933
  3. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  4. 2018YOLOv3: An Incremental Improvementcited by 2,659
  5. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  6. 2016Adversarial examples in the physical worldcited by 1,769
  7. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,630
  8. 2016YOLO9000: Better, Faster, Strongercited by 1,431
  9. 2015Spatial Transformer Networkscited by 1,429
  10. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  11. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,055
  12. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 982
  13. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 784
  14. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 737
  15. 2017Evasion Attacks against Machine Learning at Test Timecited by 689
  16. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 678
  17. 2016Stealing Machine Learning Models via Prediction APIscited by 619
  18. 2017One pixel attack for fooling deep neural networkscited by 582
  19. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 519
  20. 2017Adversarial Patchcited by 517
  21. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 462
  22. 2017Neural 3D Mesh Renderercited by 437
  23. 2014Understanding Deep Image Representations by Inverting Themcited by 403
  24. 2021Multi-Modal Fusion Transformer for End-to-End Autonomous Drivingcited by 377
  25. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 333
  26. 2020Unsupervised Discovery of Interpretable Directions in the GAN Latent Spacecited by 289
  27. 2022YOLOv6: A Single-Stage Object Detection Framework for Industrial Applicationscited by 275
  28. 2019Fooling automated surveillance cameras: adversarial patches to attack person detectioncited by 268
  29. 2017ICNet for Real-Time Semantic Segmentation on High-Resolution Imagescited by 261
  30. 2018Generating Adversarial Examples with Adversarial Networkscited by 258
  31. 2015DeepDriving: Learning Affordance for Direct Perception in Autonomous Drivingcited by 231
  32. 2013OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networkscited by 224
  33. 2015The MegaFace Benchmark: 1 Million Faces for Recognition at Scalecited by 200
  34. 2017Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimizationcited by 197
  35. 2021NEAT: Neural Attention Fields for End-to-End Autonomous Drivingcited by 174
  36. 2018Physical Adversarial Examples for Object Detectorscited by 163
  37. 2019AdvHat: Real-world adversarial attack on ArcFace Face ID systemcited by 163
  38. 2018ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detectorcited by 159

50 most cited of 132 All 132 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 6; 2025: 8; 2026: 5.

20 papers.

Sort:

By area:

  1. 2023ODDR: Outlier Detection & Dimension Reduction Based Defense Against Adversarial Patchescited by 6
  2. 2024Anomaly Unveiled: Securing Image Classification against Adversarial Patch Attackscited by 6
  3. 2024SSAP: A Shape-Sensitive Adversarial Patch for Comprehensive Disruption of Monocular Depth Estimation in Autonomous Navigation Applicationscited by 4
  4. 2024A Survey on Physical Adversarial Attacks against Face Recognition Systemscited by 4
  5. 2025Beyond Vulnerabilities: A Survey of Adversarial Attacks as Both Threats and Defenses in Computer Vision Systemscited by 4
  6. 2024Navigating Threats: A Survey of Physical Adversarial Attacks on LiDAR Perception Systems in Autonomous Vehiclescited by 3
  7. 2025A Design Framework for operationalizing Trustworthy Artificial Intelligence in Healthcare: Requirements, Tradeoffs and Challenges for its Clinical Adoptioncited by 3
  8. 2024A Simulation Framework for Electromagnetic Signal Injection Attacks on Image Sensorscited by 2
  9. 2025TESSER: Transfer-Enhancing Adversarial Attacks from Vision Transformers via Spectral and Semantic Regularizationcited by 2
  10. 2025Safe Beyond the Horizon: Efficient Sampling-based MPC with Neural Control Barrier Functionscited by 1
  11. 2025A Survey of Adversarial Defenses in Vision-based Systems: Categorization, Methods and Challengescited by 1
  12. 2025Breaking the Limits of Quantization-Aware Defenses: QADT-R for Robustness Against Patch-Based Adversarial Attacks in QNNscited by 1
8 more
  1. 2024Enhancing Mutual Trustworthiness in Federated Learning for Data-Rich Smart Citiescited by 0
  2. 2025DisPatch: Disarming Adversarial Patches in Object Detection with Diffusion Modelscited by 0
  3. 2025Projection-based Adversarial Attack using Physics-in-the-Loop Optimization for Monocular Depth Estimationcited by 0
  4. 2026PatchBlock: A Lightweight Defense Against Adversarial Patches for Embedded EdgeAI Devicescited by 0
  5. 2026AI Evasion and Impersonation Attacks on Facial Re-Identification with Activation Map Explanationscited by 0
  6. 2026AI Security Research Should Better Incentivize Defense Researchcited by 0
  7. 2026MATS: A novel multi-modality multi-task learning framework for 3D perception in autonomous drivingcited by 0
  8. 2026Printability-Constrained Adversarial Decals for Near-Nadir Aerial Perception: Measured Ink Gamuts, Nested Realism Constraints, and a Physical-World Boundcited by 0