mlsanityData to 7 Oct 2026

Evading Adversarial Example Detection Defenses with Orthogonal Projected Gradient Descent

arXiv 2106.15023 ↗First posted 28 Jun 2021cs.LG cs.CRcited by 34

Not on the map. Why?

Abstract (arXiv)

Evading adversarial example detection defenses requires finding adversarial examples that must simultaneously (a) be misclassified by the model and (b) be detected as non-adversarial. We find that existing attacks that attempt to satisfy multiple simultaneous constraints often over-optimize against one constraint at the cost of satisfying another. We introduce Orthogonal Projected Gradient Descent, an improved attack technique to generate adversarial examples that avoids this problem by orthogonalizing the gradients when running standard gradient-based attacks. We use our technique to evade four state-of-the-art detection defenses, reducing their accuracy to 0% while maintaining a 0% detection rate.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Builds on 24 of its 29 references that are in the map. First posted on arXiv 28 Jun 2021.

Builds on

24 of 29 references.

References · 24

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  5. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  6. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  7. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  8. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
  9. 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
  10. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  11. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
  12. 2018Generating Natural Language Adversarial Examplescited by 422
12 more
  1. 2017Adversarial Attacks on Neural Network Policiescited by 314
  2. 2018Certified Defenses against Adversarial Examplescited by 305
  3. 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 280
  4. 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 268
  5. 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 268
  6. 2017Detecting Adversarial Samples from Artifactscited by 244
  7. 2017On Detecting Adversarial Perturbationscited by 232
  8. 2019The Odds are Odd: A Statistical Test for Detecting Adversarial Examplescited by 75
  9. 2019Gotta Catch 'Em All: Using Honeypots to Catch Adversarial Attacks on Neural Networkscited by 40
  10. 2018Detection based Defense against Adversarial Examples from the Steganalysis Point of Viewcited by 32
  11. 2021Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform Domaincited by 29
  12. 2019DLA: Dense-Layer-Analysis for Adversarial Example Detectioncited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 7; 2023: 10; 2024: 11; 2025: 4; 2026: 2.

34 papers.

Sort:

By area:

  1. 2024Certifiably Robust RAG against Retrieval Corruptioncited by 144
  2. 2024RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysiscited by 33
  3. 2025SynthID-Image: Image watermarking at internet scalecited by 26
  4. 2022Detecting Adversarial Perturbations in Multi-Task Perceptioncited by 15
  5. 2023A LLM Assisted Exploitation of AI-Guardiancited by 14
  6. 2022Increasing Confidence in Adversarial Robustness Evaluationscited by 12
  7. 2022What You See is Not What the Network Infers: Detecting Adversarial Examples Based on Semantic Contradictioncited by 10
  8. 2023Uncertainty-weighted Loss Functions for Improved Adversarial Attacks on Semantic Segmentationcited by 9
  9. 2022Be Your Own Neighborhood: Detecting Adversarial Example by the Neighborhood Relations Built on Self-Supervised Learningcited by 5
  10. 2023PAD: Towards Principled Adversarial Malware Detection Against Evasion Attackscited by 5
  11. 2023Uncertainty-based Detection of Adversarial Attacks in Semantic Segmentationcited by 5
  12. 2023Adversarial Machine Learning for Social Good: Reframing the Adversary as an Allycited by 5
22 more
  1. 2024Systematic Categorization, Construction and Evaluation of New Attacks against Multi-modal Mobile GUI Agentscited by 5
  2. 2024Inherent Diverse Redundant Safety Mechanisms for AI-based Software Elements in Automotive Applicationscited by 4
  3. 2024Fortify the Guardian, Not the Treasure: Resilient Adversarial Detectorscited by 4
  4. 2024Input Space Mode Connectivity in Deep Neural Networkscited by 4
  5. 2023MalPurifier: Enhancing Android Malware Detection with Adversarial Purification against Evasion Attackscited by 3
  6. 2023Physics-constrained Attack against Convolution-based Human Motion Predictioncited by 2
  7. 2022White-Box Attacks on Hate-speech BERT Classifiers in German with Explicit and Implicit Character Level Defensecited by 1
  8. 2023Breaking Boundaries: Balancing Performance and Robustness in Deep Wireless Traffic Forecastingcited by 1
  9. 2024Detecting Adversarial Data using Perturbation Forgerycited by 1
  10. 2024Feature compression is the root cause of adversarial fragility in neural network classifierscited by 1
  11. 2024Detecting Adversarial Attacks in Semantic Segmentation via Uncertainty Estimation: A Deep Analysiscited by 1
  12. 2025A Few Large Shifts: Layer-Inconsistency Based Minimal Overhead Adversarial Example Detectioncited by 1
  13. 2025Adversarial Machine Learning Attacks on Financial Reporting via Maximum Violated Multi-Objective Attackcited by 1
  14. 2022Hindi/Bengali Sentiment Analysis Using Transfer Learning and Joint Dual Input Learning with Self Attentioncited by 0
  15. 2022Neighboring State-based Exploration for Reinforcement Learningcited by 0
  16. 2023A Minimax Approach Against Multi-Armed Adversarial Attacks Detectioncited by 0
  17. 2023Online Black-Box Confidence Estimation of Deep Neural Networkscited by 0
  18. 2024Optimal Zero-Shot Detector for Multi-Armed Attackscited by 0
  19. 2024Pre-trained Encoder Inference: Revealing Upstream Encoders In Downstream Machine Learning Servicescited by 0
  20. 2025Evaluating the robustness of adversarial defenses in malware detection systemscited by 0
  21. 2026USAD: Uncertainty-aware Statistical Adversarial Detectioncited by 0
  22. 2026GeoDetect: Geometric Adversarial Detection for VLPscited by 0