In the proportional high-dimensional regime, stronger backdoor training triggers improve clean accuracy and make attack success non-monotonic for regularized GLMs on Gaussian mixtures, with closed-form proofs for squared loss and fixed-point extensions to convex losses.
Backdoor Attack in the Physical World, April 2021
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
PolicyGuard provides a test-time step-level defense against backdoor attacks in RL using GP posterior variance, showing high detection AUROC on seven games.
Module-switching defense disrupts backdoors more effectively than weight averaging with fewer models and remains robust even when some models share the same backdoors.
DeTrigger detects and mitigates backdoor attacks in federated learning via gradient analysis and temperature scaling, claiming up to 251x faster detection and 98.9% attack reduction on four datasets with minimal accuracy loss.
citing papers explorer
-
When Stronger Triggers Backfire: A High-Dimensional Theory of Backdoor Attacks
In the proportional high-dimensional regime, stronger backdoor training triggers improve clean accuracy and make attack success non-monotonic for regularized GLMs on Gaussian mixtures, with closed-form proofs for squared loss and fixed-point extensions to convex losses.
-
PolicyGuard: Towards Test-time and Step-level Adversary (Backdoor) Defense for Reinforcement Learning Agent
PolicyGuard provides a test-time step-level defense against backdoor attacks in RL using GP posterior variance, showing high detection AUROC on seven games.
-
Defending against Backdoor Attacks via Module Switching
Module-switching defense disrupts backdoors more effectively than weight averaging with fewer models and remains robust even when some models share the same backdoors.
-
DeTrigger: A Gradient-Centric Approach to Backdoor Attack Mitigation in Federated Learning
DeTrigger detects and mitigates backdoor attacks in federated learning via gradient analysis and temperature scaling, claiming up to 251x faster detection and 98.9% attack reduction on four datasets with minimal accuracy loss.