mlsanityData to 14 Oct 2026

Efficient Defenses Against Adversarial Attacks

arXiv 1707.06728 ↗First posted 21 Jul 2017cs.LGcited by 53

Not on the map. Why?

Abstract (arXiv)

Following the recent adoption of deep neural networks (DNN) accross a wide range of applications, adversarial attacks against these models have proven to be an indisputable threat. Adversarial samples are crafted with a deliberate intention of undermining a system. In the case of DNNs, the lack of better understanding of their working has prevented the development of efficient defenses. In this paper, we propose a new defense method based on practical observations which is easy to integrate into models and performs better than state-of-the-art defenses. Our proposed solution is meant to reinforce the structure of a DNN, making its prediction more stable and less likely to be fooled by adversarial samples. We conduct an extensive experimental study proving the efficiency of our method against multiple attacks, comparing it to numerous defenses, both in white-box and black-box setups. Additionally, the implementation of our method brings almost no overhead to the training procedure, while maintaining the prediction performance of the original model on clean samples.

Key facts. Cited by 53 papers in the map (data through 14 Oct 2026). First posted on arXiv 21 Jul 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 18; 2022: 11; 2023: 11; 2024: 6; 2025: 4; 2026: 3.

53 papers.

Sort:

By area:

  1. 2021SoK: How Robust is Image Classification Deep Neural Network Watermarking? (Extended Version)cited by 69
  2. 2023How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defensescited by 66
  3. 2021Relating Adversarially Robust Generalization to Flat Minimacited by 57
  4. 2021Subspace Adversarial Trainingcited by 41
  5. 2021Biometrics: Trust, but Verifycited by 39
  6. 2021A Review of Adversarial Attack and Defense for Classification Methodscited by 29
  7. 2021Parameterizing Activation Functions for Adversarial Robustnesscited by 22
  8. 2024MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsificationcited by 21
  9. 2024Beyond Dropout: Robust Convolutional Neural Networks Based on Local Feature Maskingcited by 19
  10. 2021On the Inherent Regularization Effects of Noise Injection During Trainingcited by 18
  11. 2023Targeted Attack Improves Protection against Unauthorized Diffusion Customizationcited by 18
  12. 2021A PAC-Bayes Analysis of Adversarial Robustnesscited by 13
38 more
  1. 2022A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairnesscited by 13
  2. 2023FINER: Enhancing State-of-the-art Classifiers with Feature Attribution to Facilitate Security Analysiscited by 12
  3. 2022MCIBI++: Soft Mining Contextual Information Beyond Image for Semantic Segmentationcited by 10
  4. 2023Towards Robust Model Watermark via Reducing Parametric Vulnerabilitycited by 10
  5. 2021Morphence: Moving Target Defense Against Adversarial Examplescited by 9
  6. 2022Defending Against Backdoor Attack on Graph Nerual Network by Explainabilitycited by 9
  7. 2023Learning Provably Robust Estimators for Inverse Problems via Jitteringcited by 8
  8. 2023Untargeted White-box Adversarial Attack with Heuristic Defence Methods in Real-time Deep Learning based Network Intrusion Detection Systemcited by 8
  9. 2021Certification of embedded systems based on Machine Learning: A surveycited by 6
  10. 2022Robust Prototypical Few-Shot Organ Segmentation with Regularized Neural-ODEscited by 5
  11. 2021Explaining Adversarial Vulnerability with a Data Sparsity Hypothesiscited by 4
  12. 2021Trustworthy AI and Robotics and the Implications for the AEC Industry: A Systematic Literature Review and Future Potentialscited by 4
  13. 2023One-stage Modality Distillation for Incomplete Multimodal Learningcited by 4
  14. 2021Detect and Defense Against Adversarial Examples in Deep Learning using Natural Scene Statistics and Adaptive Denoisingcited by 3
  15. 2022Adversarial Machine Learning Threat Analysis and Remediation in Open Radio Access Network (O-RAN)cited by 3
  16. 2022Hessian-Free Second-Order Adversarial Examples for Adversarial Learningcited by 3
  17. 2021Countering Adversarial Examples: Combining Input Transformation and Noisy Trainingcited by 2
  18. 2022Memory Defense: More Robust Classification via a Memory-Masking Autoencodercited by 2
  19. 2022Rethinking Machine Learning Robustness via its Link with the Out-of-Distribution Problemcited by 2
  20. 2022Morphence-2.0: Evasion-Resilient Moving Target Defense Powered by Out-of-Distribution Detectioncited by 2
  21. 2023Robustness Enhancement in Neural Networks with Alpha-Stable Training Noisecited by 2
  22. 2023Panda or not Panda? Understanding Adversarial Attacks with Interactive Visualizationcited by 2
  23. 2024CausAdv: A Causal-based Framework for Detecting Adversarial Examplescited by 2
  24. 2024Enhancing Adversarial Robustness via Uncertainty-Aware Distributional Adversarial Trainingcited by 2
  25. 2021Label Smoothed Embedding Hypothesis for Out-of-Distribution Detectioncited by 1
  26. 2021CAP-GAN: Towards Adversarial Robustness with Cycle-consistent Attentional Purificationcited by 1
  27. 2022Improving Neural ODEs via Knowledge Distillationcited by 1
  28. 2024A Training Rate and Survival Heuristic for Inference and Robustness Evaluation (TRASHFIRE)cited by 1
  29. 2025ChainMarks: Securing DNN Watermark with Cryptographic Chaincited by 1
  30. 2021Adversarial examples attack based on random warm restart mechanism and improved Nesterov momentumcited by 0
  31. 2021Adversarial Machine Learning for Cybersecurity and Computer Vision: Current Developments and Challengescited by 0
  32. 2022When adversarial examples are excusablecited by 0
  33. 2023Inference Time Evidences of Adversarial Attacks for Forensic on Transformerscited by 0
  34. 2023Training Image Derivatives: Increased Accuracy and Universal Robustnesscited by 0
  35. 2024Unraveling Attacks in Machine Learning-based IoT Ecosystems: A Survey and the Open Libraries Behind Themcited by 0
  36. 2025Label Smoothing is a Pragmatic Information Bottleneckcited by 0
  37. 2025SoK: Systematic analysis of adversarial threats against deep learning approaches for autonomous anomaly detection systems in SDN-IoT networkscited by 0
  38. 2025Studying Various Activation Functions and Non-IID Data for Machine Learning Model Robustnesscited by 0

50 most cited of 53 All 53 (JSON)