mlsanityData to 7 Oct 2026

Partial train and isolate, mitigate backdoor attack

arXiv 2405.16488 ↗First posted 26 May 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Neural networks are widely known to be vulnerable to backdoor attacks, a method that poisons a portion of the training data to make the target model perform well on normal data sets, while outputting attacker-specified or random categories on the poisoned samples. Backdoor attacks are full of threats. Poisoned samples are becoming more and more similar to corresponding normal samples, and even the human eye cannot easily distinguish them. On the other hand, the accuracy of models carrying backdoors on normal samples is no different from that of clean models.In this article, by observing the characteristics of backdoor attacks, We provide a new model training method (PT) that freezes part of the model to train a model that can isolate suspicious samples. Then, on this basis, a clean model is fine-tuned to resist backdoor attacks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 36 references that are in the map. First posted on arXiv 26 May 2024.

Builds on

24 of 36 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  3. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  4. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,012
  5. 2013Speech Recognition with Deep Recurrent Neural Networkscited by 666
  6. 2018Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networkscited by 550
  7. 2018Spectral Signatures in Backdoor Attackscited by 457
  8. 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 429
  9. 2020Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networkscited by 341
  10. 2021Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networkscited by 313
  11. 2020Input-Aware Dynamic Backdoor Attackcited by 304
  12. 2019Label-Consistent Backdoor Attackscited by 285
12 more
  1. 2021Anti-Backdoor Learning: Training Clean Models on Poisoned Datacited by 258
  2. 2019A new Backdoor Attack in CNNs by training set corruption without label poisoningcited by 237
  3. 2020Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustnesscited by 130
  4. 2019Transferable Clean-Label Poisoning Attacks on Deep Neural Netscited by 129
  5. 2020Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Casescited by 93
  6. 2020Strong Data Augmentation Sanitizes Poisoning and Backdoor Attacks Without an Accuracy Tradeoffcited by 86
  7. 2019Defending Neural Backdoors via Generative Distribution Modelingcited by 82
  8. 2020DeepSweep: An Evaluation Framework for Mitigating DNN Backdoor Attacks using Data Augmentationcited by 75
  9. 2023Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimizationcited by 60
  10. 2020Computing Systems for Autonomous Driving: State-of-the-Art and Challengescited by 47
  11. 2021Few-shot Backdoor Defense Using Shapley Estimationcited by 40
  12. 2020Defending against Backdoor Attack on Deep Neural Networkscited by 22

Built on by

Not cited yet.