AI Paper Atlas

Research map / Adversarial robustness and security / Backdoor and poisoning

ProFlip: Targeted Trojan Attack With Progressive Bit Flips

Huili Chen, Cheng Fu, Jishen Zhao, Farinaz Koushanfar

ICCV 2021 · Adversarial robustness and security › Backdoor and poisoning · approach: Trigger-based backdoor attacks · 76 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 progressive critical bits search with parameter sensitivity instead of TBT's last-layer fine-tuningProFlip vs TBT · CIFAR-10 ResNet-18bit flips: 413 -> 12Improved
select the vulnerable parameter by fitness score (psens=45) instead of last-layer weights (psens=60) (ablation)ProFlip BFA · SVHN VGG-16ASR: 73.8 -> 94.5Improved
increase trigger area from 6.25% to 11.82% (ablation)ProFlip · CIFAR-10 ResNet-18bit flips: 42 -> 3Improved
increase trigger area from 6.25% to 11.82% (ablation)ProFlip trigger generation · CIFAR-10 ResNet-18trigger ASR: 25.65 -> 66.3Improved
increase clean sample size from 64 to 256 images (ablation)ProFlip · CIFAR-10 ResNet-18ASR: 95.7 -> 97.9Improved
increase clean sample size from 256 to 1024 (ablation)ProFlip · CIFAR-10 ResNet-18ASR: 97.9 -> 97.9No clear effect
vary target class (class 6 vs class 2) (ablation)ProFlip · CIFAR-10 ResNet-18bit flips: 12 -> 4Mixed
increase gamma1 from 1 to 8 in Trojan loss (ablation)ProFlip · CIFAR-10 ResNet-18ASR / test accuracy: ASR 97.68 -> 96.31; TA 89.44 -> 90.38Mixed
decompose the most vulnerable parameter as a defenseProFlip · CIFAR-10 ResNet-18ASR: 97.9 -> 73.7Hurt
decompose the most vulnerable parameter as a defenseProFlip · CIFAR-10 ResNet-18bit flips: 12 -> 111Improved
decompose top-3 sensitive parameters of VGG-16 as a defenseProFlip · SVHN VGG-16bit flips: 20 -> 124Improved

Later papers that compared with this method

3 later accepted papers report ProFlip as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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