AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

Consensus Learning with Multi-Party Perturbation Triggers for Secure Model Access

Yizhun Zhang, Jie Huang, Zeping Zhang, Shuaishuai Zhang, Changhao Ding, Xuan Chen

AAAI 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Membership inference and inversion

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
protect model with CPTM consensus triggersResNet18 · CIFAR-10 (5 clients)accuracy on authorized data: 93.08 -> 93.33No clear effect
protect model with CPTM consensus triggersVGG16 · CIFAR-100 (5 clients)accuracy on authorized data: 70.19 -> 67.63Hurt
protect model with CPTM consensus triggersDenseNet · CIFAR-10 (5 clients)accuracy on authorized data: 95.39 -> 93.45Hurt
feed original unauthorized inputs to the protected modelCPTM protected models · CIFAR-10, CIFAR-100, Face-LFWaccuracy: 93.33 -> 0.56Hurt
attacker uses a single client's perturbation to craft triggers (ablation)CPTM protected ResNet18 · CIFAR-10attacker accuracy: 0.56 -> 1.90No clear effect
attacker fuses perturbations from three of five clients (ablation)CPTM protected VGG16 · CIFAR-10attacker accuracy: 1.31 -> 15.08Improved
attacker uses a single client's perturbation (ablation)CPTM protected DenseNet · MNISTattacker accuracy: 10.37 -> 17.16Improved
increase number of clients from 5 to 20 (ablation)CPTM on ResNet18 · CIFAR-10Acc-Pro: 93.33 -> 93.02No clear effect
increase number of clients from 5 to 20 (ablation)CPTM on ResNet18 · CIFAR-10Acc-Origin: 0.56 -> 0.72No clear effect
attacker extracts trigger features from partial consensus data and applies them to own samplesCPTM protected models · trigger extraction attack, four datasetsattacker accuracyNo clear effect

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