mlsanityData to 14 Oct 2026

Discerning the Chaos: Detecting Adversarial Perturbations while Disentangling Intentional from Unintentional Noises

arXiv 2409.19619 ↗First posted 29 Sep 2024cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep learning models, such as those used for face recognition and attribute prediction, are susceptible to manipulations like adversarial noise and unintentional noise, including Gaussian and impulse noise. This paper introduces CIAI, a Class-Independent Adversarial Intent detection network built on a modified vision transformer with detection layers. CIAI employs a novel loss function that combines Maximum Mean Discrepancy and Center Loss to detect both intentional (adversarial attacks) and unintentional noise, regardless of the image class. It is trained in a multi-step fashion. We also introduce the aspect of intent during detection that can act as an added layer of security. We further showcase the performance of our proposed detector on CelebA, CelebA-HQ, LFW, AgeDB, and CIFAR-10 datasets. Our detector is able to detect both intentional (like FGSM, PGD, and DeepFool) and unintentional (like Gaussian and Salt & Pepper noises) perturbations.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 40 of its 51 references that are in the map. First posted on arXiv 29 Sep 2024.

Builds on

40 of 51 references.

References · 40

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  6. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  7. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  8. 2016Adversarial examples in the physical worldcited by 1,769
  9. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  10. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  11. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  12. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
28 more
  1. 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
  2. 2020Fast is better than free: Revisiting adversarial trainingcited by 727
  3. 2017One pixel attack for fooling deep neural networkscited by 582
  4. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 486
  5. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  6. 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 355
  7. 2016Learning from Simulated and Unsupervised Images through Adversarial Trainingcited by 288
  8. 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 282
  9. 2017On Detecting Adversarial Perturbationscited by 232
  10. 2018SparseFool: a few pixels make a big differencecited by 94
  11. 2021Delving Deep into the Generalization of Vision Transformers under Distribution Shiftscited by 85
  12. 2019Detecting Adversarial Samples Using Influence Functions and Nearest Neighborscited by 72
  13. 2021A Survey On Universal Adversarial Attackcited by 59
  14. 2016Examining the Impact of Blur on Recognition by Convolutional Networkscited by 58
  15. 2019A New Defense Against Adversarial Images: Turning a Weakness into a Strengthcited by 49
  16. 2020Maximum Mean Discrepancy Test is Aware of Adversarial Attackscited by 44
  17. 2021PRIME: A few primitives can boost robustness to common corruptionscited by 40
  18. 2018Unravelling Robustness of Deep Learning based Face Recognition Against Adversarial Attackscited by 31
  19. 2021Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform Domaincited by 29
  20. 2022GRIT: General Robust Image Task Benchmarkcited by 26
  21. 2022Pixle: a fast and effective black-box attack based on rearranging pixelscited by 20
  22. 2022Adversarial Patch Attacks and Defences in Vision-Based Tasks: A Surveycited by 17
  23. 2021Back in Black: A Comparative Evaluation of Recent State-Of-The-Art Black-Box Attackscited by 16
  24. 2017Quality Resilient Deep Neural Networkscited by 12
  25. 2017AFIF4: Deep Gender Classification based on AdaBoost-based Fusion of Isolated Facial Features and Foggy Facescited by 12
  26. 2022Unfolding Local Growth Rate Estimates for (Almost) Perfect Adversarial Detectioncited by 5
  27. 2023Detecting Adversarial Faces Using Only Real Face Self-Perturbationscited by 4
  28. 2023Continual Adversarial Defensecited by 4

Built on by

Not cited yet.