mlsanityData to 7 Oct 2026

AntidoteRT: Run-time Detection and Correction of Poison Attacks on Neural Networks

arXiv 2202.01179 ↗First posted 31 Jan 2022cs.CR cs.CVcited by 0

On the map: LLM safety and security → Backdoor and data poisoning attacks

Abstract (arXiv)

We study backdoor poisoning attacks against image classification networks, whereby an attacker inserts a trigger into a subset of the training data, in such a way that at test time, this trigger causes the classifier to predict some target class. %There are several techniques proposed in the literature that aim to detect the attack but only a few also propose to defend against it, and they typically involve retraining the network which is not always possible in practice. We propose lightweight automated detection and correction techniques against poisoning attacks, which are based on neuron patterns mined from the network using a small set of clean and poisoned test samples with known labels. The patterns built based on the mis-classified samples are used for run-time detection of new poisoned inputs. For correction, we propose an input correction technique that uses a differential analysis to identify the trigger in the detected poisoned images, which is then reset to a neutral color. Our detection and correction are performed at run-time and input level, which is in contrast to most existing work that is focused on offline model-level defenses. We demonstrate that our technique outperforms existing defenses such as NeuralCleanse and STRIP on popular benchmarks such as MNIST, CIFAR-10, and GTSRB against the popular BadNets attack and the more complex DFST attack.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security. Builds on 17 of its 31 references that are in the map. First posted on arXiv 31 Jan 2022.

Builds on

17 of 31 references.

References · 17

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  2. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 936
  3. 2018Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networkscited by 550
  4. 2018Spectral Signatures in Backdoor Attackscited by 457
  5. 2019STRIP: A Defence Against Trojan Attacks on Deep Neural Networkscited by 437
  6. 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 429
  7. 2020Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networkscited by 341
  8. 2021Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networkscited by 313
  9. 2017Certified Defenses for Data Poisoning Attackscited by 288
  10. 2019Detecting AI Trojans Using Meta Neural Analysiscited by 192
  11. 2017Neural Trojanscited by 151
  12. 2019Universal Litmus Patterns: Revealing Backdoor Attacks in CNNscited by 143
5 more
  1. 2020Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Casescited by 93
  2. 2020Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxificationcited by 93
  3. 2020Rethinking the Trigger of Backdoor Attackcited by 76
  4. 2019Model Agnostic Defence against Backdoor Attacks in Machine Learningcited by 52
  5. 2020Removing Backdoor-Based Watermarks in Neural Networks with Limited Datacited by 23

Built on by

Not cited yet.