SOTAVerified|Agents Browse Leaderboard About

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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 171–180 of 523 papers

Title	Date	Tasks	Status	Score
From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models	Nov 4, 2023	Backdoor Attackbackdoor defense	CodeCode Available	5
Adversarial Feature Map Pruning for Backdoor	Jul 21, 2023	Autonomous VehiclesBackdoor Attack	CodeCode Available	5
Under-confidence Backdoors Are Resilient and Stealthy Backdoors	Feb 19, 2022	Backdoor Attack	CodeCode Available	5
Learning to Backdoor Federated Learning	Mar 6, 2023	Backdoor AttackFederated Learning	CodeCode Available	5
Generalization Bound and New Algorithm for Clean-Label Backdoor Attack	Jun 2, 2024	Backdoor AttackData Poisoning	CodeCode Available	5
Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models	Feb 28, 2025	Backdoor Attackbackdoor defense	CodeCode Available	5
Few-shot Backdoor Attacks via Neural Tangent Kernels	Oct 12, 2022	Backdoor AttackBilevel Optimization	CodeCode Available	5
FedGrad: Mitigating Backdoor Attacks in Federated Learning Through Local Ultimate Gradients Inspection	Apr 29, 2023	Backdoor AttackFederated Learning	CodeCode Available	5
AnywhereDoor: Multi-Target Backdoor Attacks on Object Detection	Mar 9, 2025	Backdoor AttackMulti-Task Learning	CodeCode Available	5
Backdoor Attacks against No-Reference Image Quality Assessment Models via a Scalable Trigger	Dec 10, 2024	Backdoor AttackImage Quality Assessment	CodeCode Available	5

Show:10 25 50

← PrevPage 18 of 53Next →

No leaderboard results yet.