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 326–350 of 523 papers

TitleStatusHype
Unnoticeable Backdoor Attacks on Graph Neural NetworksCode1
Training-free Lexical Backdoor Attacks on Language ModelsCode0
Revisiting Personalized Federated Learning: Robustness Against Backdoor Attacks—0
Gradient Shaping: Enhancing Backdoor Attack Against Reverse Engineering—0
BDMMT: Backdoor Sample Detection for Language Models through Model Mutation Testing—0
Backdoor Attacks in Peer-to-Peer Federated Learning—0
On the Vulnerability of Backdoor Defenses for Federated LearningCode1
BEAGLE: Forensics of Deep Learning Backdoor Attack for Better DefenseCode1
Universal Detection of Backdoor Attacks via Density-based Clustering and Centroids AnalysisCode0
Silent Killer: A Stealthy, Clean-Label, Black-Box Backdoor AttackCode1
Backdoor Attacks Against Dataset DistillationCode1
SSDA: Secure Source-Free Domain AdaptationCode0
You Are Catching My Attention: Are Vision Transformers Bad Learners Under Backdoor Attacks?—0
Color Backdoor: A Robust Poisoning Attack in Color SpaceCode0
Mind Your Heart: Stealthy Backdoor Attack on Dynamic Deep Neural Network in Edge ComputingCode0
Vulnerabilities of Deep Learning-Driven Semantic Communications to Backdoor (Trojan) Attacks—0
VSVC: Backdoor attack against Keyword Spotting based on Voiceprint Selection and Voice Conversion—0
AI Security for Geoscience and Remote Sensing: Challenges and Future Trends—0
Backdoor Attack Detection in Computer Vision by Applying Matrix Factorization on the Weights of Deep Networks—0
How to Backdoor Diffusion Models?Code1
Be Careful with Rotation: A Uniform Backdoor Pattern for 3D Shape—0
BadPrompt: Backdoor Attacks on Continuous PromptsCode1
A Survey on Backdoor Attack and Defense in Natural Language Processing—0
Invisible Backdoor Attack with Dynamic Triggers against Person Re-identificationCode0
PBSM: Backdoor attack against Keyword spotting based on pitch boosting and sound masking—0
Show:102550
← PrevPage 14 of 21Next →

No leaderboard results yet.