Pith. sign in

REVIEW 1 cited by

A Dual Stealthy Backdoor: From Both Spatial and Frequency Perspectives

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2307.10184 v1 pith:YMRTLRN7 submitted 2023-07-03 cs.CR cs.AIcs.LG

classification cs.CRcs.AIcs.LG
keywords attacktriggersbackdoorimagestealthinessfrequencycleandomain
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Backdoor attacks pose serious security threats to deep neural networks (DNNs). Backdoored models make arbitrarily (targeted) incorrect predictions on inputs embedded with well-designed triggers while behaving normally on clean inputs. Many works have explored the invisibility of backdoor triggers to improve attack stealthiness. However, most of them only consider the invisibility in the spatial domain without explicitly accounting for the generation of invisible triggers in the frequency domain, making the generated poisoned images be easily detected by recent defense methods. To address this issue, in this paper, we propose a DUal stealthy BAckdoor attack method named DUBA, which simultaneously considers the invisibility of triggers in both the spatial and frequency domains, to achieve desirable attack performance, while ensuring strong stealthiness. Specifically, we first use Discrete Wavelet Transform to embed the high-frequency information of the trigger image into the clean image to ensure attack effectiveness. Then, to attain strong stealthiness, we incorporate Fourier Transform and Discrete Cosine Transform to mix the poisoned image and clean image in the frequency domain. Moreover, the proposed DUBA adopts a novel attack strategy, in which the model is trained with weak triggers and attacked with strong triggers to further enhance the attack performance and stealthiness. We extensively evaluate DUBA against popular image classifiers on four datasets. The results demonstrate that it significantly outperforms the state-of-the-art backdoor attacks in terms of the attack success rate and stealthiness

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution

    cs.LG 2024-11 conditional novelty 5.0 of 10

    VERT defends federated learning against large-scale model poisoning by selecting, in each round, the users whose gradients best match an autoregressive prediction from each user's own history.

Pith tools