TrojDRL: Evaluation of Backdoor Attacks on Deep Reinforcement Learning
Open accessThe DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Abstract
We present TrojDRL, a tool for exploring and evaluating backdoor attacks on deep reinforcement learning agents. TrojDRL exploits the sequential nature of deep reinforcement learning (DRL) and considers different gradations of threat models. We show that untargeted attacks on state-of-the-art actor-critic algorithms can circumvent existing defenses built on the assumption of backdoors being targeted. We evaluated TrojDRL on a broad set of DRL benchmarks and showed that the attacks require only poisoning as little as 0.025% of the training data. Compared with existing works of backdoor attacks on classification models, TrojDRL provides a first step towards understanding the vulnerability of DRL agents.
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
Asynchronous Methods for Deep Reinforcement Learning
Mnih, V., Badia, A. P., Mirza, M., Graves, A., Lillicrap, T. P., Harley, T., Silver, D., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1602.01783 · Cited by 7,132 · cited 5×
“• We develop the first demonstration of backdoor attacks on A3C [8], a state-of-the-art DRL algorithm.”
BackgroundMethodInfluentialPractical Black-Box Attacks against Machine Learning
Papernot, N., McDaniel, P., Goodfellow, I., Jha, S., Celik, Z. B., & Swami, A. (2017) · Proceedings of the 2017 ACM on Asia Conference on Computer and Communications Security · doi:10.1145/3052973.3053009 · Cited by 3,495
Self-citationDeep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
Nguyen, A., Yosinski, J., & Clune, J. (2014) · arXiv · doi:10.48550/arxiv.1412.1897 · Cited by 3,258
Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
Nguyen, A., Yosinski, J., & Clune, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298640 · Cited by 3,258
Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples
Athalye, A., Carlini, N., & Wagner, D. (2018) · arXiv · doi:10.48550/arxiv.1802.00420 · Cited by 2,172 · cited 1×
“Studies towards evaluating the robustness of neural networks show that defending against this type of attack is very challenging [13], [14].”
BackgroundThe Arcade Learning Environment: An Evaluation Platform for General Agents
Bellemare, M. G., Naddaf, Y., Veness, J., & Bowling, M. (2013) · Journal of Artificial Intelligence Research · doi:10.1613/jair.3912 · Cited by 2,161 · cited 1×
“This algorithm interfaces with the Atari library implemented in [24] which offers a variety of environments for the Atari 2600 games.”
MethodDelving into Transferable Adversarial Examples and Black-box Attacks
Liu, Y., Chen, X., Liu, C., & Song, D. (2016) · arXiv · doi:10.48550/arxiv.1611.02770 · Cited by 1,310
Trojaning Attack on Neural Networks
Liu, Y., Ma, S., Aafer, Y., Lee, W.-C., Zhai, J., Wang, W., & Zhang, X. (2018) · Proceedings 2018 Network and Distributed System Security Symposium · doi:10.14722/ndss.2018.23291 · Cited by 1,270
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 · cited 1×
“When the training data or procedure is accessible by the attacker, such as in the case of outsourced training, recent works have shown that an adversary can craft Trojaned or backdoored models in supervised learning settings [3], [4], [7].”
BackgroundDetecting Backdoor Attacks on Deep Neural Networks by Activation Clustering
Chen, B., Carvalho, W., Baracaldo, N., Ludwig, H., Edwards, B., Lee, T., Molloy, I., & Srivastava, B. (2018) · arXiv · doi:10.48550/arxiv.1811.03728 · Cited by 485
DeepInspect: A Black-box Trojan Detection and Mitigation Framework for Deep Neural Networks
Chen, H., Fu, C., Zhao, J., & Koushanfar, F. (2019) · Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/647 · Cited by 314
Cited by
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
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
“, a symbol on the screen of an Atari game) [85], [96].”
BackgroundChallenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learning
Ilahi, I., Usama, M., Qadir, J., Janjua, M. U., Al-Fuqaha, A., Hoang, D. T., & Niyato, D. (2022) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2021.3111139 · Cited by 170
Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning
Cinà, A. E., Grosse, K., Demontis, A., Vascon, S., Zellinger, W., Moser, B. A., Oprea, A., Biggio, B., Pelillo, M., & Roli, F. (2023) · ACM Computing Surveys · doi:10.1145/3585385 · Cited by 152
Trusted AI in Multiagent Systems: An Overview of Privacy and Security for Distributed Learning
Ma, C., Li, J., Wei, K., Liu, B., Ding, M., Yuan, L., Han, Z., & Vincent Poor, H. (2023) · Proceedings of the IEEE · doi:10.1109/jproc.2023.3306773 · Cited by 96
Metadata
- Authors
- Kiourti, P., Wardega, K., Jha, S., & Li, W.
- Venue
- 2020 57th ACM/IEEE Design Automation Conference (DAC)
- Publisher
- IEEE
- Published
- 2020-07
- Pages
- 1-6
- ISSN
- 0738-100X (ISSN-L)
- OpenAlex
- W3092005433
- Cited by
- 70
- References
- 12
- FWCI
- 3.63
- Type
- conference paper
- 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.