mlsanityData to 7 Oct 2026

Protecting the Neural Networks against FGSM Attack Using Machine Unlearning

arXiv 2511.01377 ↗First posted 3 Nov 2025cs.LGcited by 0

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

Machine learning is a powerful tool for building predictive models. However, it is vulnerable to adversarial attacks. Fast Gradient Sign Method (FGSM) attacks are a common type of adversarial attack that adds small perturbations to input data to trick a model into misclassifying it. In response to these attacks, researchers have developed methods for "unlearning" these attacks, which involves retraining a model on the original data without the added perturbations. Machine unlearning is a technique that tries to "forget" specific data points from the training dataset, to improve the robustness of a machine learning model against adversarial attacks like FGSM. In this paper, we focus on applying unlearning techniques to the LeNet neural network, a popular architecture for image classification. We evaluate the efficacy of unlearning FGSM attacks on the LeNet network and find that it can significantly improve its robustness against these types of attacks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 18 of its 26 references that are in the map. First posted on arXiv 3 Nov 2025.

Builds on

18 of 26 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Machine Unlearning: its nature, scope, and importance for a "delete culture"24 May
  2. 2023Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy10 May

Other references · 16

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  4. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  5. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  6. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  7. 2016Stealing Machine Learning Models via Prediction APIscited by 602
  8. 2018Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networkscited by 550
  9. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  10. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
  11. 2018Analyzing Federated Learning through an Adversarial Lenscited by 346
  12. 2018PRADA: Protecting against DNN Model Stealing Attackscited by 159
4 more
  1. 2019Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attackscited by 79
  2. 2021An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defencescited by 41
  3. 2021ML Attack Models: Adversarial Attacks and Data Poisoning Attackscited by 23
  4. 2018Defend Deep Neural Networks Against Adversarial Examples via Fixed and Dynamic Quantized Activation Functionscited by 17

Built on by

Not cited yet.