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 451–460 of 523 papers

TitleStatusHype
Dual Model Replacement:invisible Multi-target Backdoor Attack based on Federal Learning—0
Dynamic Backdoor Attacks Against Machine Learning Models—0
Dyn-Backdoor: Backdoor Attack on Dynamic Link Prediction—0
EEG-Based Brain-Computer Interfaces Are Vulnerable to Backdoor Attacks—0
Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats—0
ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models—0
EmoAttack: Emotion-to-Image Diffusion Models for Emotional Backdoor Generation—0
EmoAttack: Utilizing Emotional Voice Conversion for Speech Backdoor Attacks on Deep Speech Classification Models—0
Enhancing Adversarial Training with Prior Knowledge Distillation for Robust Image Compression—0
Enhancing Clean Label Backdoor Attack with Two-phase Specific Triggers—0
Show:102550
← PrevPage 46 of 53Next →

No leaderboard results yet.