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 491–500 of 523 papers

TitleStatusHype
Injecting Bias into Text Classification Models using Backdoor Attacks—0
Invisible Backdoor Attacks Using Data Poisoning in the Frequency Domain—0
Invisible Backdoor Attack Through Singular Value Decomposition—0
Invisible Threats: Backdoor Attack in OCR Systems—0
Is It Possible to Backdoor Face Forgery Detection with Natural Triggers?—0
Is Multi-Modal Necessarily Better? Robustness Evaluation of Multi-modal Fake News Detection—0
Jigsaw Puzzle: Selective Backdoor Attack to Subvert Malware Classifiers—0
Krait: A Backdoor Attack Against Graph Prompt Tuning—0
LADDER: Multi-objective Backdoor Attack via Evolutionary Algorithm—0
Large Language Models are Good Attackers: Efficient and Stealthy Textual Backdoor Attacks—0
Show:102550
← PrevPage 50 of 53Next →

No leaderboard results yet.