mlsanityData to 7 Oct 2026

SafetyNet: Detecting and Rejecting Adversarial Examples Robustly

arXiv 1704.00103 ↗First posted 1 Apr 2017cs.CV cs.LGcited by 76

Not on the map. Why?

Abstract (arXiv)

We describe a method to produce a network where current methods such as DeepFool have great difficulty producing adversarial samples. Our construction suggests some insights into how deep networks work. We provide a reasonable analyses that our construction is difficult to defeat, and show experimentally that our method is hard to defeat with both Type I and Type II attacks using several standard networks and datasets. This SafetyNet architecture is used to an important and novel application SceneProof, which can reliably detect whether an image is a picture of a real scene or not. SceneProof applies to images captured with depth maps (RGBD images) and checks if a pair of image and depth map is consistent. It relies on the relative difficulty of producing naturalistic depth maps for images in post processing. We demonstrate that our SafetyNet is robust to adversarial examples built from currently known attacking approaches.

Key facts. Cited by 76 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 36; 2022: 14; 2023: 11; 2024: 11; 2025: 4.

76 papers.

Sort:

By area:

  1. 2024Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systemscited by 63
  2. 2021Adversarial Example Detection for DNN Models: A Review and Experimental Comparisoncited by 51
  3. 2021Optical Adversarial Attackcited by 43
  4. 2021WaveGuard: Understanding and Mitigating Audio Adversarial Examplescited by 39
  5. 2021Transporting Causal Mechanisms for Unsupervised Domain Adaptationcited by 38
  6. 2022Fooling the Eyes of Autonomous Vehicles: Robust Physical Adversarial Examples Against Traffic Sign Recognition Systemscited by 27
  7. 2021Inconspicuous Adversarial Patches for Fooling Image Recognition Systems on Mobile Devicescited by 18
  8. 2021MagDR: Mask-guided Detection and Reconstruction for Defending Deepfakescited by 17
  9. 2021Adversarial Imaging Pipelinescited by 15
  10. 2021Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution Viewcited by 15
  11. 2021Attack as Defense: Characterizing Adversarial Examples using Robustnesscited by 14
  12. 2021Two Coupled Rejection Metrics Can Tell Adversarial Examples Apartcited by 14
38 more
  1. 2023Adv-Bot: Realistic Adversarial Botnet Attacks against Network Intrusion Detection Systemscited by 14
  2. 2023Defenses in Adversarial Machine Learning: A Surveycited by 14
  3. 2021Interpreting Attributions and Interactions of Adversarial Attackscited by 13
  4. 2023HybridAugment++: Unified Frequency Spectra Perturbations for Model Robustnesscited by 12
  5. 2023Dynamic Adversarial Attacks on Autonomous Driving Systemscited by 11
  6. 2024Trustworthy Federated Learning: Privacy, Security, and Beyondcited by 11
  7. 2021Resilient Machine Learning for Networked Cyber Physical Systems: A Survey for Machine Learning Security to Securing Machine Learning for CPScited by 10
  8. 2021AGKD-BML: Defense Against Adversarial Attack by Attention Guided Knowledge Distillation and Bi-directional Metric Learningcited by 10
  9. 2021DeepAdversaries: Examining the Robustness of Deep Learning Models for Galaxy Morphology Classificationcited by 10
  10. 2021Revisiting Model's Uncertainty and Confidences for Adversarial Example Detectioncited by 9
  11. 2021SoK: Machine Learning Governancecited by 9
  12. 2022Threat Assessment in Machine Learning based Systemscited by 9
  13. 2021Detecting Textual Adversarial Examples through Randomized Substitution and Votecited by 8
  14. 2023Defense against Adversarial Cloud Attack on Remote Sensing Salient Object Detectioncited by 8
  15. 2021Self-Supervised Adversarial Example Detection by Disentangled Representationcited by 7
  16. 2022TAD: Transfer Learning-based Multi-Adversarial Detection of Evasion Attacks against Network Intrusion Detection Systemscited by 7
  17. 2021Adversarial Learning with Cost-Sensitive Classescited by 6
  18. 2021Key Technology Considerations in Developing and Deploying Machine Learning Models in Clinical Radiology Practicecited by 6
  19. 2021Towards Adversarial Patch Analysis and Certified Defense against Crowd Countingcited by 6
  20. 2021We Can Always Catch You: Detecting Adversarial Patched Objects WITH or WITHOUT Signaturecited by 6
  21. 2022How Robust are Discriminatively Trained Zero-Shot Learning Models?cited by 6
  22. 2022Certified Adversarial Robustness via Anisotropic Randomized Smoothingcited by 6
  23. 2021End-to-end Uncertainty-based Mitigation of Adversarial Attacks to Automated Lane Centeringcited by 5
  24. 2021All You Need is RAW: Defending Against Adversarial Attacks with Camera Image Pipelinescited by 5
  25. 2023Certifiable Black-Box Attacks with Randomized Adversarial Examples: Breaking Defenses with Provable Confidencecited by 5
  26. 2024Adversarial Feature Alignment: Balancing Robustness and Accuracy in Deep Learning via Adversarial Trainingcited by 5
  27. 2021Explaining Adversarial Vulnerability with a Data Sparsity Hypothesiscited by 4
  28. 2022Boosting Adversarial Robustness From The Perspective of Effective Margin Regularizationcited by 4
  29. 2024Fortify the Guardian, Not the Treasure: Resilient Adversarial Detectorscited by 4
  30. 2021Anomaly Detection of Adversarial Examples using Class-conditional Generative Adversarial Networkscited by 3
  31. 2021Detect and Defense Against Adversarial Examples in Deep Learning using Natural Scene Statistics and Adaptive Denoisingcited by 3
  32. 2021Reconstruction guided Meta-learning for Few Shot Open Set Recognitioncited by 3
  33. 2021Mitigating Black-Box Adversarial Attacks via Output Noise Perturbationcited by 3
  34. 2021Unity is strength: Improving the Detection of Adversarial Examples with Ensemble Approachescited by 3
  35. 2022Wavelet Regularization Benefits Adversarial Trainingcited by 3
  36. 2022Secure and Trustworthy Artificial Intelligence-Extended Reality (AI-XR) for Metaversescited by 3
  37. 2023Adversarial Medical Image with Hierarchical Feature Hidingcited by 3
  38. 2022A Tutorial on Adversarial Learning Attacks and Countermeasurescited by 2

50 most cited of 76 All 76 (JSON)