Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 158

The DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.

BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning

Open access
Jia, Jinyuan, Liu, Yupei, Gong, Neil Zhenqiang · 2022 · 2022 IEEE Symposium on Security and Privacy (SP)

Abstract

Self-supervised learning in computer vision aims to pre-train an image encoder using a large amount of unlabeled images or (image, text) pairs. The pre-trained image encoder can then be used as a feature extractor to build downstream classifiers for many downstream tasks with a small amount of or no labeled training data. In this work, we propose BadEncoder, the first backdoor attack to self-supervised learning. In particular, our BadEncoder injects backdoors into a pre-trained image encoder such that the downstream classifiers built based on the backdoored image encoder for different downstream tasks simultaneously inherit the backdoor behavior. We formulate our BadEncoder as an optimization problem and we propose a gradient descent based method to solve it, which produces a backdoored image encoder from a clean one. Our extensive empirical evaluation results on multiple datasets show that our BadEncoder achieves high attack success rates while preserving the accuracy of the downstream classifiers. We also show the effectiveness of BadEncoder using two publicly available, real-world image encoders, i.e., Google’s image encoder pre-trained on ImageNet and OpenAI’s Contrastive Language-Image Pre-training (CLIP) image encoder pre-trained on 400 million (image, text) pairs collected from the Internet. Moreover, we consider defenses including Neural Cleanse and MNTD (empirical defenses) as well as PatchGuard (a provable defense). Our results show that these defenses are insufficient to defend against BadEncoder, highlighting the needs for new defenses against our BadEncoder. Our code is publicly available at: https://github.com/jjy1994/BadEncoder.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/sp46214.2022.9833644

Cites

17 of 17 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

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

Show all 17 references

Cited by

See all 158

Metadata

Authors
Jia, J., Liu, Y., & Gong, N. Z.
Venue
2022 IEEE Symposium on Security and Privacy (SP)
Publisher
IEEE
Published
2022-05
Pages
2043-2059
ISSN
1081-6011 (ISSN-L)
OpenAlex
W3189812816
Cited by
158
References
17
FWCI
19.47
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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning. https://app.cochat.ai/papers/10.1109/sp46214.2022.9833644
The paper
Jia, J., Liu, Y., & Gong, N. Z. (2022). BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning. 2022 IEEE Symposium on Security and Privacy (SP). https://doi.org/10.1109/sp46214.2022.9833644

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.