AI Paper Atlas

Research map / Adversarial robustness and security / Backdoor and poisoning

Authority Backdoor: A Certifiable Backdoor Mechanism for Authoring DNNs

Han Yang, Shaofeng Li, Tian Dong, Xiangyu Xu, Guangchi Liu, Zhen Ling

AAAI 2026 · Adversarial robustness and security › Backdoor and poisoning · approach: Trigger-based backdoor attacks · 0 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 randomized smoothing (sigma=0.9) to the authority backdoorResNet-18 Authority Backdoor · CIFAR-10 adaptive attackacc_reversed: 94.26% -> 14.18%Improved
add randomized smoothing (sigma=0.9) to the authority backdoorResNet-18 Authority Backdoor · CIFAR-10acc_auth: 94.13% -> 78.48%Hurt
add randomized smoothingResNet-18 Authority Backdoor · GTSRBacc_auth: 98.55% -> 62.75%Hurt
add randomized smoothingResNet-18 Authority Backdoor · TinyImageNetacc_reversed: 14.10% -> 12.86%No clear effect
increase smoothing noise sigma from 0.4 to 0.9 (ablation)ResNet-18 Authority Backdoor · CIFAR-10acc_reversed: 54.5% -> baseline level (acc_clean)Improved
increase smoothing noise sigma from 0.4 to 0.9 (ablation)ResNet-18 Authority Backdoor · CIFAR-10acc_auth: 86.2% -> 73.9%Hurt
add negative-loss finetuning during implantingAuthority Backdoor · clean finetuning attack, 100 samples 10 epochsacc_clean: 0.55% -> 0.15%Improved
add negative-loss finetuning during implantingAuthority Backdoor · clean finetuning attackacc_auth: 89.33% -> 89.31%No clear effect
Authority Backdoor vs AdvParamsResNet-18 · CIFAR-10acc_auth: 92.02% -> 94.13%Improved
Authority Backdoor vs PassportsResNet-18 · CIFAR-10acc_auth: 90.89% -> 94.13%Improved
Authority Backdoor vs AdvParamsResNet-18 · GTSRBacc_clean: 6.94% -> 9.40%Hurt
apply vanilla adaptive attack to unsmoothed modelResNet-18 Authority Backdoor · CIFAR-10restored accuracy: 6.02% -> 91.84%Hurt

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