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 351–360 of 523 papers

TitleStatusHype
ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMs—0
Show Me Your Code! Kill Code Poisoning: A Lightweight Method Based on Code Naturalness—0
Single-Node Trigger Backdoor Attacks in Graph-Based Recommendation Systems—0
SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents—0
SOS! Soft Prompt Attack Against Open-Source Large Language Models—0
SSL-OTA: Unveiling Backdoor Threats in Self-Supervised Learning for Object Detection—0
Stealthy and Robust Backdoor Attack against 3D Point Clouds through Additional Point Features—0
Stealthy Backdoor Attack in Self-Supervised Learning Vision Encoders for Large Vision Language Models—0
Stealthy Backdoor Attack to Real-world Models in Android Apps—0
Stealthy Patch-Wise Backdoor Attack in 3D Point Cloud via Curvature Awareness—0
Show:102550
← PrevPage 36 of 53Next →

No leaderboard results yet.