AI Paper Atlas

Research map / Adversarial robustness and security / Backdoor and poisoning

Backdoor Attacks on Neural Networks via One-Bit Flip

Xiang Li, Lannan Luo, Qiang Zeng

ICCV 2025 · Adversarial robustness and security › Backdoor and poisoning · approach: Trigger-based backdoor attacks · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add the bit flip to the generated trigger (ablation)SOLEFLIP · CIFAR-10 ResNet-18ASR (%): 13.2 -> 99.8Improved
add the generated trigger to the bit flip (ablation)SOLEFLIP · CIFAR-10 ResNet-18ASR (%): 9.9 -> 99.8Improved
add the bit flip to the generated trigger (ablation)SOLEFLIP · SVHN VGG-16ASR (%): 13.1 -> 97.6Improved
add the generated trigger to the bit flip (ablation)SOLEFLIP · SVHN VGG-16ASR (%): 15.8 -> 97.6Improved
add the bit flip to the generated trigger (ablation)SOLEFLIP · ImageNet ResNet-18ASR (%): 0.8 -> 99.9Improved
add the generated trigger to the bit flip (ablation)SOLEFLIP · ImageNet ResNet-18ASR (%): 0.1 -> 99.9Improved
increase lambda from 0.001 to 0.003 (ablation)SOLEFLIP · CIFAR-10 ResNet-18ASR: 0.998 -> 0.980Mixed
increase lambda from 0.001 to 0.003 (ablation)SOLEFLIP · CIFAR-10 trigger stealthinessTAP (%): 8.70 -> 4.70Improved
increase sample set size (ablation)SOLEFLIP · CIFAR-10 ResNet-18neuron outputImproved
increase sample set size (ablation)SOLEFLIP · CIFAR-10 ResNet-18trigger L1 normNo clear effect
use 4-bit instead of 8-bit quantization (ablation)SOLEFLIP · CIFAR-10 ResNet-18ASR (%): 99.8 -> 99.77No clear effect
use SOLEFLIP one-bit flip instead of multi-bit TBTSOLEFLIP · CIFAR-10 ResNet-18BAD (%): 4.0 -> 0.0Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy