AI Paper Atlas

Research map / Adversarial robustness and security / Backdoor and poisoning

Versatile Backdoor Attack With Visible, Semantic, Sample-Specific and Compatible Triggers

Ruotong Wang, Hongrui Chen, Zihao Zhu, Li Liu, Baoyuan Wu

TPAMI 2025 · Adversarial robustness and security › Backdoor and poisoning · approach: Trigger-based backdoor attacks · 16 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 fine-grained trigger selection (reject low-ISR triggers) (ablation)VSSC attack · ImageNet-Dogs and FOOD-11, digitalASR: actual poisoning only 0.91% and 8.34% for low-quality triggers at preset 10%Improved
add quality assessment module (VLM check) to poisoned sample generation (ablation)VSSC attack · image classification, ResNet-18, digitalASR: maximum increase of 10.11% in ASRImproved
use advanced diffusion image editing (Null-text Inversion) instead of patching or InstructPix2Pix for trigger insertion (ablation)VSSC attack · physical scenario classificationASRImproved
raise poisoning ratio from 5% to 30% (ablation)VSSC (red flower) · ImageNet-Dogs physical, ResNet-18ASR (%): 65.00 -> 89.00Improved
raise poisoning ratio from 5% to 30% (ablation)VSSC (strawberry) · FOOD-11 physical, VGG19-BNASR (%): 61.00 -> 100.00Improved
use VSSC semantic trigger instead of BadNets patch on clean accuracyVSSC · classification digitalC-Acc: less than 2% C-Acc decreaseImproved
use VSSC trigger instead of baselines under print-and-recapture distortionVSSC · ImageNet-Dogs D2P, ResNet-18ASR (%): WaNet 76.19 -> VSSC 97.62Improved
move from digital to digital-to-physical scenarioVSSC · face verificationASR: decreases by an average of only 5.81%Hurt
add VSSC trigger vs baseline triggers under D2P in face verificationbaselines · face verification D2PASR: decrease in ASR up to 32.13%Hurt
apply DDE defense to VSSCVSSC_1 (ResNet-18) · ImageNet-Dogs 5% under defensesASR (%): 87.79No clear effect
apply ABL defense to VSSC_2 versus BadNetsVSSC_2 · ImageNet-Dogs 5%ASR (%): VSSC_2 73.85 vs BadNets 1.86Mixed
insert trigger only into compatible classes (collar on animals) (ablation)VSSC · animals and vehicles datasetASRNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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