AI Paper Atlas

Research map / Adversarial robustness and security / Certified and empirical robustness

Robust Learning for Data Poisoning Attacks

Yunjuan Wang, Poorya Mianjy, Raman Arora

ICML 2021 · Adversarial robustness and security › Certified and empirical robustness · approach: Robustness to poisoning and multiple attacks

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 negated loss instead of original cross-entropy when generating PGA poisoning attackspoisoning attack generation (regime A) · MNIST linear model and CIFAR10 AlexNetclean test accuracy under poisoningImproved
train two-layer ReLU networks with SGD while widening network into a moderate range (not too wide)two-layer ReLU networks under poisoning · MNIST and CIFAR10clean test accuracy vs widthMixed
increase overall perturbation budget S beyond about sqrt(n) (corruption rate above ~250)SGD on linear model under clean-label poisoning · MNIST linear modelexcess error and excess loss vs sample sizeHurt
increase corruption budget with sample size (sublinear overall perturbation)SGD on convex learning problems · theory (Theorem 2.2)excess risk boundNo 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