Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 285

The DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.

Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examples

Open access
Liu, Zihao, Liu, Qi, Liu, Tao, Xu, Nuo, Lin, Xue, Wang, Yanzhi, Wen, Wujie·2019·2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Abstract

Image compression-based approaches for defending against the adversarial-example attacks, which threaten the safety use of deep neural networks (DNN), have been investigated recently. However, prior works mainly rely on directly tuning parameters like compression rate, to blindly reduce image features, thereby lacking guarantee on both defense efficiency (i.e. accuracy of polluted images) and classification accuracy of benign images, after applying defense methods. To overcome these limitations, we propose a JPEG-based defensive compression framework, namely “feature distillation”, to effectively rectify adversarial examples without impacting classification accuracy on benign data. Our framework significantly escalates the defense efficiency with marginal accuracy reduction using a twostep method: First, we maximize malicious features filtering of adversarial input perturbations by developing defensive quantization in frequency domain of JPEG compression or decompression, guided by a semi-analytical method; Second, we suppress the distortions of benign features to restore classification accuracy through a DNN-oriented quantization refine process. Our experimental results show that proposed “feature distillation” can significantly surpass the latest input-transformation based mitigations such as Quilting and TV Minimization in three aspects, including defense efficiency (improve classification accuracy from ∼ 20% to ∼ 90% on adversarial examples), accuracy of benign images after defense (≤ 1% accuracy degradation), and processing time per image (∼ 259× Speedup). Moreover, our solution also can provide the best defense efficiency (∼ 60% accuracy) against the latest BPDA attack with least accuracy reduction (∼ 1%) on benign images among all other input-transformation based defense methods.

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/cvpr.2019.00095

Cites

27 of 27 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 27 references

Metadata

Authors
Liu, Z., Liu, Q., Liu, T., Xu, N., Lin, X., Wang, Y., & Wen, W.
Venue
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2019-06
Pages
860-868
ISSN
1063-6919 (ISSN-L)
OpenAlex
W2963384482
Cited by
285
References
27
FWCI
12.02
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: Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examples. https://app.cochat.ai/papers/10.1109/cvpr.2019.00095
The paper
Liu, Z., Liu, Q., Liu, T., Xu, N., Lin, X., Wang, Y., & Wen, W. (2019). Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examples. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr.2019.00095

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.