AI Paper Atlas

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

Identification of the Adversary from a Single Adversarial Example

Minhao Cheng, Rui Min, Haochen Sun, Pin-Yu Chen

ICML 2023 · 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
Random mask watermarking embedded in head layers of each copymodel copies (VGG16, ResNet18) · CIFAR-10, GTSRB, Tiny-ImageNetclassification accuracy: worst drop about 1%No clear effect
Adding data-limited adversary identification score (perturbation on masked pixels + adversarial stability)data-limited tracing · CIFAR-10, GTSRB, Tiny-ImageNet, single adversarial exampletracing accuracy: average 71.33%, random guess 1%Improved
Data-free max label score for tracingdata-free tracing · CIFAR-10, GTSRB, Tiny-ImageNet, single adversarial exampletracing accuracy: average 69.80% vs 71.33% data-limited; SignOPT up about 23 pointsMixed
Data-free detector instead of data-limited detector on SignOPT attackSignOPT adversarial examples · CIFAR-10, GTSRB, Tiny-ImageNettracing accuracy: about 23% improvementImproved
Data-limited detector applied to Bandit attackBandit adversarial examples · CIFAR-10, GTSRB, Tiny-ImageNettracing accuracy: worst case just over 42%Hurt
Combining multiple adversarial examples (summing scores) (ablation)data-limited and data-free tracing · CIFAR-10, 100 copiestracing accuracy: around 97% with 1 example, 100% with 3 or moreImproved
Increasing noise level on watermark pixels (adaptive attack) on data-limited detector (ablation)data-limited tracing · CIFAR-10 ResNet18, adaptive attacktracing accuracy: significant accuracy dropHurt
Random-noise adaptive attack on data-free detector (ablation)data-free tracing · CIFAR-10 ResNet18, adaptive attacktracing accuracy: not sensitive to random noiseNo clear effect
Increasing alpha weight on adversarial stability term (ablation)data-limited tracing · CIFAR-10 and GTSRB, Bandit and SignOPTtracing accuracy: qualitativeImproved
Increasing alpha weight on adversarial stability term (ablation)data-limited tracing · CIFAR-10 and GTSRB, HSJ NES SimBAtracing accuracy: slight dropHurt

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