AI Paper Atlas

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

Exploring Model Dynamics for Accumulative Poisoning Discovery

Jianing Zhu, Xiawei Guo, Jiangchao Yao, Chao Du, LI He, Shuo Yuan, Tongliang Liu, Liang Wang, Bo Han

ICML 2023 · Adversarial robustness and security › Attacks on text and graphs · approach: Clean-label data poisoning · 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
Use discrepancy-aware selective sample correctionResNet-18 · CIFAR-10, CIFAR-100, and SVHN Accu. Poisontest accuracy + Trigger (%): CIFAR-10: 75.3±0.26 -> 77.3±0.58; SVHN: 88.7±0.20 -> 88.8±0.26; CIFAR-100: 44.4±0.21 -> 45.4±1.39Improved
Apply DSC rather than adversarial training to clean samplesResNet-18 · CIFAR-10 Clean Oracletest accuracy (%): 77.2 -> 84.7Improved
Use a later Epoch 30 auxiliary model without adjusting the discrepancy threshold (ablation)DSC on ResNet-18 · CIFAR-10 Accu. Poisontest accuracy + Trigger (%): 77.3±0.58% -> 63.6±3.39%Hurt
Adjust P when using the Epoch 30 auxiliary model (ablation)DSC on ResNet-18 · CIFAR-10 Accu. Poisontest accuracy + Trigger (%): 63.6±3.39% -> 76.8±0.27%Improved
Replace DSC correction with TRADES, MART, MMD, or FAT correction (ablation)ResNet-18 · CIFAR-10 Accu. Poisontest accuracy + Trigger (%): DSC: 77.3±0.58%; TRADES: 72.5±0.45%; MART: 68.4±0.66%; MMD: 71.4±0.77%; FAT: 76.2±0.23%Hurt
Use KL (TRADES) instead of PGD for the adversarial optimization loss (ablation)DSC on ResNet-18 · CIFAR-10 Accu. Poisontest accuracy + Trigger (%): 78.7 -> 77.3Hurt
Use CW∞ instead of PGD for the adversarial optimization loss (ablation)DSC on ResNet-18 · CIFAR-10 Accu. Poisontest accuracy + Trigger (%): 78.7 -> 79.3Improved
Increase the adaptive attack constraint β (ablation)Accumulative poisoning attacker against ST · CIFAR-10 adaptive attacktest accuracy + Trigger (%): 51.3 -> 74.9Mixed
Use a black-box Epoch 10 surrogate rather than the white-box setting (ablation)DSC on ResNet-18 · CIFAR-10 Accu. Poisontest accuracy + Trigger (%): 77.3±0.58% -> 79.7±0.03%Improved

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