Rethinking Backdoor Data Poisoning Attacks in the Context of Semi-Supervised Learning
On the map: LLM safety and security → Backdoor and data poisoning attacks
Abstract (arXiv)
Semi-supervised learning methods can train high-accuracy machine learning models with a fraction of the labeled training samples required for traditional supervised learning. Such methods do not typically involve close review of the unlabeled training samples, making them tempting targets for data poisoning attacks. In this paper we investigate the vulnerabilities of semi-supervised learning methods to backdoor data poisoning attacks on the unlabeled samples. We show that simple poisoning attacks that influence the distribution of the poisoned samples' predicted labels are highly effective - achieving an average attack success rate as high as 96.9%. We introduce a generalized attack framework targeting semi-supervised learning methods to better understand and exploit their limitations and to motivate future defense strategies.
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 30 of its 38 references that are in the map. First posted on arXiv 5 Dec 2022.
Builds on
30 of 38 references.
References · 30
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2016Wide Residual Networkscited by 3,057
- 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
- 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
- 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
- 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
- 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
- 2018Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networkscited by 550
- 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 500
- 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
- 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 429
- 2019Hidden Trigger Backdoor Attackscited by 359
18 more
- 2019ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoringcited by 349
- 2021A Survey on Deep Semi-supervised Learningcited by 250
- 2021Adversarial Neuron Pruning Purifies Backdoored Deep Modelscited by 230
- 2020Clean-Label Backdoor Attacks on Video Recognition Modelscited by 162
- 2020Witches' Brew: Industrial Scale Data Poisoning via Gradient Matchingcited by 156
- 2017Neural Trojanscited by 151
- 2019Universal Litmus Patterns: Revealing Backdoor Attacks in CNNscited by 143
- 2019Transferable Clean-Label Poisoning Attacks on Deep Neural Netscited by 129
- 2019TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systemscited by 120
- 2020MetaPoison: Practical General-purpose Clean-label Data Poisoningcited by 114
- 2020Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attackscited by 109
- 2019Defending Neural Backdoors via Generative Distribution Modelingcited by 82
- 2020Rethinking the Trigger of Backdoor Attackcited by 76
- 2020Bullseye Polytope: A Scalable Clean-Label Poisoning Attack with Improved Transferabilitycited by 65
- 2021Poisoning the Unlabeled Dataset of Semi-Supervised Learningcited by 44
- 2019A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learningcited by 30
- 2022The Perils of Learning From Unlabeled Data: Backdoor Attacks on Semi-supervised Learningcited by 9
- 2020Influence-Driven Data Poisoning in Graph-Based Semi-Supervised Classifierscited by 2
Built on by
Not cited yet.