SOTAVerified

Backdoor Attack

Backdoor attacks inject maliciously constructed data into a training set so that, at test time, the trained model misclassifies inputs patched with a backdoor trigger as an adversarially-desired target class.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 181–190 of 523 papers

TitleStatusHype
DarkMind: Latent Chain-of-Thought Backdoor in Customized LLMs—0
BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning—0
DeTrigger: A Gradient-Centric Approach to Backdoor Attack Mitigation in Federated Learning—0
Cooperative Backdoor Attack in Decentralized Reinforcement Learning with Theoretical Guarantee—0
Contributor-Aware Defenses Against Adversarial Backdoor Attacks—0
DeBackdoor: A Deductive Framework for Detecting Backdoor Attacks on Deep Models with Limited Data—0
Debiasing Backdoor Attack: A Benign Application of Backdoor Attack in Eliminating Data Bias—0
Backdoor Attack with Imperceptible Input and Latent Modification—0
Deep Learning Backdoors—0
Confidence Matters: Inspecting Backdoors in Deep Neural Networks via Distribution Transfer—0
Show:102550
← PrevPage 19 of 53Next →

No leaderboard results yet.