Backdoor Attacks Against Transfer Learning With Pre-Trained Deep Learning Models
Open accessThe DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
Transfer learning provides an effective solution for feasibly and fast customize accurateStudentmodels, by transferring the learned knowledge of pre-trainedTeachermodels over large datasets via fine-tuning. Many pre-trained Teacher models used in transfer learning are publicly available and maintained by public platforms, increasing their vulnerability to backdoor attacks. In this article, we demonstrate a backdoor threat to transfer learning tasks on both image and time-series data leveraging the knowledge of publicly accessible Teacher models, aimed at defeating three commonly adopted defenses:pruning-based,retraining-basedandinput pre-processing-based defenses. Specifically, ($\mathcal {A}$A) ranking-based selection mechanism to speed up the backdoor trigger generation and perturbation process while defeatingpruning-basedand/orretraining-based defenses. ($\mathcal {B}$B) autoencoder-powered trigger generation is proposed to produce a robust trigger that can defeat theinput pre-processing-based defense, while guaranteeing that selected neuron(s) can be significantly activated. ($\mathcal {C}$C) defense-aware retraining to generate the manipulated model using reverse-engineered model inputs. We launch effective misclassification attacks on Student models over real-world images, brain Magnetic Resonance Imaging (MRI) data and Electrocardiography (ECG) learning systems. The experiments reveal that our enhanced attack can maintain the 98.4 and 97.2 percent classification accuracy as the genuine model on clean image and time series inputs while improving$27.9\%-100\%$27.9%-100%and$27.1\%-56.1\%$27.1%-56.1%attack success rate on trojaned image and time series inputs respectively in the presence of pruning-based and/or retraining-based defenses.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Towards Evaluating the Robustness of Neural Networks
Carlini, N., & Wagner, D. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.49 · Cited by 8,859
Han, S., Mao, H., & Dally, W. J. (2015) · arXiv · doi:10.48550/arxiv.1510.00149 · Cited by 4,662
Pruning Filters for Efficient ConvNets
Li, H., Kadav, A., Durdanovic, I., Samet, H., & Graf, H. P. (2016) · arXiv · doi:10.48550/arxiv.1608.08710 · Cited by 2,928
Learning both Weights and Connections for Efficient Neural Networks
Han, S., Pool, J., Tran, J., & Dally, W. J. (2015) · arXiv · doi:10.48550/arxiv.1506.02626 · Cited by 1,481
Poisoning Attacks against Support Vector Machines
Biggio, B., Nelson, B., & Laskov, P. (2012) · arXiv · doi:10.48550/arxiv.1206.6389 · Cited by 1,331
BadNets: Evaluating Backdooring Attacks on Deep Neural Networks
Gu, T., Liu, K., Dolan-Gavitt, B., & Garg, S. (2019) · IEEE Access · doi:10.1109/access.2019.2909068 · Cited by 1,238
Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks
Liu, K., Dolan-Gavitt, B., & Garg, S. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-00470-5_13 · Cited by 1,055
Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
Chen, X., Liu, C., Li, B., Lu, K., & Song, D. (2017) · arXiv · doi:10.48550/arxiv.1712.05526 · Cited by 1,039
Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization
Muñoz-González, L., Biggio, B., Demontis, A., Paudice, A., Wongrassamee, V., Lupu, E. C., & Roli, F. (2017) · Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security · doi:10.1145/3128572.3140451 · Cited by 549
Liu, Y., Xie, Y., & Srivastava, A. (2017) · 2017 IEEE International Conference on Computer Design (ICCD) · doi:10.1109/iccd.2017.16 · Cited by 241
Cited by
Machine learning and deep learning
Janiesch, C., Zschech, P., & Heinrich, K. (2021) · Electronic Markets · doi:10.1007/s12525-021-00475-2 · Cited by 2,959
Li, Y., Jiang, Y., Li, Z., & Xia, S.-T. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3182979 · Cited by 682
Zhang, W., Deng, L., Zhang, L., & Wu, D. (2023) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2022.106004 · Cited by 427
Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses
Goldblum, M., Tsipras, D., Xie, C., Chen, X., Schwarzschild, A., Song, D., Madry, A., Li, B., & Goldstein, T. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3162397 · Cited by 362
Machine Learning for Security in Vehicular Networks: A Comprehensive Survey
Talpur, A., & Gurusamy, M. (2022) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2021.3129079 · Cited by 107
The Threat of Offensive AI to Organizations
Mirsky, Y., Demontis, A., Kotak, J., Shankar, R., Gelei, D., Yang, L., Zhang, X., Pintor, M., Lee, W., Elovici, Y., et al. (2023) · Computers & Security · doi:10.1016/j.cose.2022.103006 · Cited by 97
MARNet: Backdoor Attacks Against Cooperative Multi-Agent Reinforcement Learning
Chen, Y., Zheng, Z., & Gong, X. (2023) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2022.3207429 · Cited by 32
Metadata
- Authors
- Wang, S., Nepal, S., Rudolph, C., Grobler, M., Chen, S., & Chen, T.
- Venue
- IEEE Transactions on Services Computing
- Published
- 2022-05-01
- Volume
- 15
- Issue
- 3
- Pages
- 1526-1539
- ISSN
- 1939-1374 (ISSN-L)
- 2372-0204
- OpenAlex
- W2999321020
- Cited by
- 80
- References
- 10
- FWCI
- 2.75
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.