Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information
Open accessThe DOI matches its Crossref record; 25 of the 25 references it cites were found in a registry or an index.
Abstract
Backdoor attacks introduce manipulated data into a machine learning model's training set, causing the model to misclassify inputs with a trigger during testing to achieve a desired outcome by the attacker. For backdoor attacks to bypass human inspection, it is essential that the injected data appear to be correctly labeled. The attacks with such property are often referred to as "clean-label attacks." The success of current clean-label backdoor methods largely depends on access to the complete training set. Yet, accessing the complete dataset is often challenging or unfeasible since it frequently comes from varied, independent sources, like images from distinct users. It remains a question of whether backdoor attacks still present real threats.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 8×
“For most of the evaluations, except the ablation study on target and surrogate model mismatch, we use the widely-adopted ResNet-18 [29] as the target model architecture.”
BackgroundMethodInfluentialGoing deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473
The unreasonable effectiveness of deep features as a perceptual metric
Zhang, R., Isola, P., Efros, A. A., Shechtman, E., & Wang, O. (2018) · arXiv · doi:10.48550/arxiv.1801.03924 · Cited by 24,812
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
Zhang, R., Isola, P., Efros, A. A., Shechtman, E., & Wang, O. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00068 · Cited by 14,623
Deep Learning Face Attributes in the Wild
Liu, Z., Luo, P., Wang, X., & Tang, X. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.425 · Cited by 7,747
Zagoruyko, S., & Komodakis, N. (2016) · Procedings of the British Machine Vision Conference 2016 · doi:10.5244/c.30.87 · Cited by 7,244
SGDR: Stochastic Gradient Descent with Warm Restarts
Loshchilov, I., & Hutter, F. (2016) · arXiv · doi:10.48550/arxiv.1608.03983 · Cited by 5,309
An overview of gradient descent optimization algorithms
Ruder, S. (2016) · arXiv · doi:10.48550/arxiv.1609.04747 · Cited by 4,962
Attribute and simile classifiers for face verification
Kumar, N., Berg, A. C., Belhumeur, P. N., & Nayar, S. K. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459250 · Cited by 1,361
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 · cited 2×
“We also adapt two standard dirty-label attacks, namely, BadNets [10] (denoted by BadNets-c) and the Blend [5] (denoted by Blend-c), to the clean-label setting by 1 LC has two modes: the GAN-based and the adversarial-perturbation-based attack.”
BackgroundMethodFine-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 · cited 6×
“Most of the existing backdoor attacks [4], [5], [9], [15], [17], [19]–[22] fall into this category.”
BackgroundMethodInfluentialNeural Networks: Tricks of the Trade
(1998) · Lecture Notes in Computer Science · doi:10.1007/3-540-49430-8 · Cited by 810
STRIP: a defence against trojan attacks on deep neural networks
Gao, Y., Xu, C., Wang, D., Chen, S., Ranasinghe, D. C., & Nepal, S. (2019) · Proceedings of the 35th Annual Computer Security Applications Conference · doi:10.1145/3359789.3359790 · Cited by 707 · cited 3×
“[8, 34, 52, 56] We study a popular test-time filtering defense, STRIP [8], as well as a state-of-the-art detection based on high-frequency artifacts synthesis [56].”
BackgroundMethodLi, 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
Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks
Liu, Y., Ma, X., Bailey, J., & Lu, F. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58607-2_11 · Cited by 531
Invisible Backdoor Attacks on Deep Neural Networks via Steganography and Regularization
Li, S., Xue, M., Zhao, B., Zhu, H., & Zhang, X. (2020) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2020.3021407 · Cited by 310 · cited 2×
“Most of the existing backdoor attacks [4], [5], [9], [15], [17], [19]–[22] fall into this category.”
BackgroundGeometric Dataset Distances via Optimal TransportPreprint
Alvarez-Melis, D., & Fusi, N. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.02923 · Cited by 271
Rethinking the Backdoor Attacks’ Triggers: A Frequency Perspective
Zeng, Y., Park, W., Mao, Z. M., & Jia, R. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01616 · Cited by 193
Self-citationUnderstanding Adversarial Examples From the Mutual Influence of Images and Perturbations
Zhang, C., Benz, P., Imtiaz, T., & Kweon, I. S. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.01453 · Cited by 181
Input-Aware Dynamic Backdoor Attack
Nguyen, A., & Tran, A. T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.08138 · Cited by 150
Model Orthogonalization: Class Distance Hardening in Neural Networks for Better Security
Tao, G., Liu, Y., Shen, G., Xu, Q., An, S., Zhang, Z., & Zhang, X. (2022) · IEEE Symposium on Security and Privacy (S&P) · doi:10.1109/sp46214.2022.9833688 · Cited by 72
Training with More Confidence: Mitigating Injected and Natural Backdoors During Training
Wang, Z., Ding, H., Zhai, J., & Ma, S. (2022) · neural information processing systems · doi:10.52202/068431-2637 · Cited by 62
Hidden Trigger Backdoor Attacks
Saha, A., Subramanya, A., & Pirsiavash, H. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6871 · Cited by 13
Cited by
Privacy and Robustness in Federated Learning: Attacks and Defenses
Lyu, L., Yu, H., Ma, X., Chen, C., Sun, L., Zhao, J., Yang, Q., & Yu, P. S. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3216981 · Cited by 548
“Besides, SMC-based protocols can enable multiple participants to collaboratively compute an agreed-upon function without leaking input information from any participant except for what can be inferred from the outcomes of the computation [99], [100].”
BackgroundSelf-citationImproving Substation Network Security with DevSecOps and AIOps
Yu, W., Qian, J., Xu, R., Jin, C., Fang, H., & Shi, X. (2024) · 2024 IEEE 10th Conference on Big Data Security on Cloud (BigDataSecurity) · doi:10.1109/bigdatasecurity62737.2024.00027 · Cited by 3
Metadata
- Authors
- Zeng, Y., Pan, M., Just, H. A., Lyu, L., Qiu, M., & Jia, R.
- Venue
- Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security
- Publisher
- ACM
- Published
- 2023-11-15
- Pages
- 771-785
- OpenAlex
- W4388867373
- Cited by
- 197
- References
- 25
- FWCI
- 36.67
- Type
- conference paper
- Language
- en
- Open access
- hybrid
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.