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 21–30 of 523 papers

TitleStatusHype
Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion ModelsCode0
Erased but Not Forgotten: How Backdoors Compromise Concept Erasure—0
SFIBA: Spatial-based Full-target Invisible Backdoor Attacks—0
BadMoE: Backdooring Mixture-of-Experts LLMs via Optimizing Routing Triggers and Infecting Dormant Experts—0
Robo-Troj: Attacking LLM-based Task Planners—0
BadApex: Backdoor Attack Based on Adaptive Optimization Mechanism of Black-box Large Language Models—0
Strategic Planning of Stealthy Backdoor Attacks in Markov Decision Processes—0
Exploring Backdoor Attack and Defense for LLM-empowered Recommendations—0
Parasite: A Steganography-based Backdoor Attack Framework for Diffusion Models—0
ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMs—0
Show:102550
← PrevPage 3 of 53Next →

No leaderboard results yet.