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 201–210 of 523 papers

Title	Date	Tasks	Status	Score
Diff-Cleanse: Identifying and Mitigating Backdoor Attacks in Diffusion Models	Jul 31, 2024	Backdoor Attackbackdoor defense	CodeCode Available	5
Exploiting the Vulnerability of Large Language Models via Defense-Aware Architectural Backdoor	Sep 3, 2024	Backdoor AttackLarge Language Model	CodeCode Available	5
EmInspector: Combating Backdoor Attacks in Federated Self-Supervised Learning Through Embedding Inspection	May 21, 2024	Backdoor AttackSelf-Supervised Learning	CodeCode Available	5
Defending Neural Backdoors via Generative Distribution Modeling	Oct 10, 2019	Backdoor AttackImage Generation	CodeCode Available	5
Backdoor Attack on Unpaired Medical Image-Text Foundation Models: A Pilot Study on MedCLIP	Jan 1, 2024	Backdoor AttackContrastive Learning	CodeCode Available	5
Energy Backdoor Attack to Deep Neural Networks	Jan 14, 2025	Backdoor Attack	CodeCode Available	5
Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion Models	Apr 29, 2025	Backdoor Attack	CodeCode Available	5
Anomaly Localization in Model Gradients Under Backdoor Attacks Against Federated Learning	Nov 29, 2021	Anomaly LocalizationBackdoor Attack	CodeCode Available	5
Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios	Jun 14, 2023	Backdoor Attack	CodeCode Available	5
BadRL: Sparse Targeted Backdoor Attack Against Reinforcement Learning	Dec 19, 2023	Backdoor Attackreinforcement-learning	CodeCode Available	5

Show:10 25 50

← PrevPage 21 of 53Next →

No leaderboard results yet.