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

Showing 401425 of 523 papers

TitleStatusHype
Is Multi-Modal Necessarily Better? Robustness Evaluation of Multi-modal Fake News Detection0
Jigsaw Puzzle: Selective Backdoor Attack to Subvert Malware Classifiers0
Krait: A Backdoor Attack Against Graph Prompt Tuning0
LADDER: Multi-objective Backdoor Attack via Evolutionary Algorithm0
Large Language Models are Good Attackers: Efficient and Stealthy Textual Backdoor Attacks0
LaserGuider: A Laser Based Physical Backdoor Attack against Deep Neural Networks0
INK: Inheritable Natural Backdoor Attack Against Model Distillation0
Let's Focus: Focused Backdoor Attack against Federated Transfer Learning0
Light Can Hack Your Face! Black-box Backdoor Attack on Face Recognition Systems0
LoBAM: LoRA-Based Backdoor Attack on Model Merging0
Long-Tailed Backdoor Attack Using Dynamic Data Augmentation Operations0
Low-Frequency Black-Box Backdoor Attack via Evolutionary Algorithm0
Low-Loss Subspace Compression for Clean Gains against Multi-Agent Backdoor Attacks0
LSP Framework: A Compensatory Model for Defeating Trigger Reverse Engineering via Label Smoothing Poisoning0
Lurking in the shadows: Unveiling Stealthy Backdoor Attacks against Personalized Federated Learning0
Marksman Backdoor: Backdoor Attacks with Arbitrary Target Class0
MARNET: Backdoor Attacks against Value-Decomposition Multi-Agent Reinforcement Learning0
MASTERKEY: Practical Backdoor Attack Against Speaker Verification Systems0
Megatron: Evasive Clean-Label Backdoor Attacks against Vision Transformer0
MEGen: Generative Backdoor in Large Language Models via Model Editing0
Memory Backdoor Attacks on Neural Networks0
ME: Trigger Element Combination Backdoor Attack on Copyright Infringement0
iBA: Backdoor Attack on 3D Point Cloud via Reconstructing Itself0
Invisible Backdoor Attack with Dynamic Triggers against Person Re-identificationCode0
Invisible Backdoor Triggers in Image Editing Model via Deep WatermarkingCode0
Show:102550
← PrevPage 17 of 21Next →

No leaderboard results yet.