Deep Neural Backdoor in Semi-Supervised Learning: Threats and Countermeasures
- 29 September 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 16 (15566013) , 4827-4842
Abstract
Semi-Supervised Learning (SSL) is a powerful derivative for humans to discover the hidden knowledge, and will be a great substitute for data taggers. Although the availability of unlabeled data rises up a huge passion to SSL, the untrustness of unlabeled data leads to many unknown security risks. In this paper, we first identify an insidious backdoor threat of SSL where unlabeled training data are poisoned by backdoor methods migrated from supervised settings. Then, to further exploit this threat, a Deep Neural Backdoor (DeNeB) scheme is proposed, which requires less data poisoning budgets and produces stronger backdoor effectiveness. By poisoning a fraction of our unlabeled training data, the DeNeB achieves the illegal manipulation on the trained model without modifying the training process. Finally, an efficient detection-and-purification defense (DePuD) framework is proposed to thwart the proposed scheme. In DePuD, we construct a deep detector to locate trigger patterns in the unlabeled training data, and perform secured SSL training with purified unlabeled data where the detected trigger patterns are obfuscated. Extensive experiments based on benchmark datasets are performed to demonstrate the huge threatening of DeNeB and the effectiveness of DePuD. To the best of our knowledge, this is the first work to achieve the backdoor and its defense in semi-supervised learning.Keywords
Funding Information
- National Natural Science Foundation of China (61971283, U20B2048, 61972255)
- Shanghai Sailing Program (21YF1421700)
- Shanghai Municipal Science and Technology Major Project (2021SHZDZX0102)
This publication has 15 references indexed in Scilit:
- DeSVig: Decentralized Swift Vigilance Against Adversarial Attacks in Industrial Artificial Intelligence SystemsIEEE Transactions on Industrial Informatics, 2019
- Label Propagation for Deep Semi-Supervised Learning2019
- Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks2019
- BadNets: Evaluating Backdooring Attacks on Deep Neural NetworksIEEE Access, 2019
- Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks2018
- Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- Trojaning Attack on Neural Networks2018
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization2017
- Backdoor attacks against learning systems2017
- Wide Residual Networks2016