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 5175 of 523 papers

TitleStatusHype
Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic TriggerCode1
Hidden Trigger Backdoor AttacksCode1
Imperceptible and Robust Backdoor Attack in 3D Point CloudCode1
Imperceptible Backdoor Attack: From Input Space to Feature RepresentationCode1
Backdoor Attack with Sparse and Invisible TriggerCode1
Backdoor Attack against Speaker VerificationCode1
A new Backdoor Attack in CNNs by training set corruption without label poisoningCode1
Label Poisoning is All You NeedCode1
Mask-based Invisible Backdoor Attacks on Object DetectionCode1
Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style TransferCode1
BadCM: Invisible Backdoor Attack Against Cross-Modal LearningCode1
Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety AlignmentCode1
BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive LearningCode1
BadEdit: Backdooring large language models by model editingCode1
Backdoor Defense via Deconfounded Representation LearningCode1
BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised LearningCode1
Anti-Backdoor Learning: Training Clean Models on Poisoned DataCode1
Backdoor Attacks Against Dataset DistillationCode1
Anti-Distillation Backdoor Attacks: Backdoors Can Really Survive in Knowledge DistillationCode1
BadMerging: Backdoor Attacks Against Model MergingCode1
Backdoor Attacks on Crowd CountingCode1
Backdoor Attacks on Federated Learning with Lottery Ticket HypothesisCode1
BEAGLE: Forensics of Deep Learning Backdoor Attack for Better DefenseCode1
Backdoor Attacks for Remote Sensing Data with Wavelet TransformCode1
Backdoor Attack on Hash-based Image Retrieval via Clean-label Data PoisoningCode1
Show:102550
← PrevPage 3 of 21Next →

No leaderboard results yet.