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 261–270 of 523 papers

TitleStatusHype
BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models—0
BadMoE: Backdooring Mixture-of-Experts LLMs via Optimizing Routing Triggers and Infecting Dormant Experts—0
BadNL: Backdoor Attacks against NLP Models with Semantic-preserving Improvements—0
BadNL: Backdoor Attacks Against NLP Models—0
BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models—0
BadSAD: Clean-Label Backdoor Attacks against Deep Semi-Supervised Anomaly Detection—0
BadSAM: Exploring Security Vulnerabilities of SAM via Backdoor Attacks—0
BadScan: An Architectural Backdoor Attack on Visual State Space Models—0
BadSFL: Backdoor Attack against Scaffold Federated Learning—0
EventTrojan: Manipulating Non-Intrusive Speech Quality Assessment via Imperceptible Events—0
Show:102550
← PrevPage 27 of 53Next →

No leaderboard results yet.