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 131–140 of 523 papers

Title	Date	Tasks	Status	Score
Invisible Backdoor Attack with Dynamic Triggers against Person Re-identification	Nov 20, 2022	AllBackdoor Attack	CodeCode Available	5
Backdooring Bias into Text-to-Image Models	Jun 21, 2024	Backdoor AttackImage Generation	CodeCode Available	5
Backdoor Pre-trained Models Can Transfer to All	Oct 30, 2021	AllBackdoor Attack	CodeCode Available	5
Under-confidence Backdoors Are Resilient and Stealthy Backdoors	Feb 19, 2022	Backdoor Attack	CodeCode Available	5
Watch Out! Simple Horizontal Class Backdoor Can Trivially Evade Defense	Oct 1, 2023	Backdoor AttackMedical Diagnosis	CodeCode Available	5
Attacks on fairness in Federated Learning	Nov 21, 2023	AttributeBackdoor Attack	CodeCode Available	5
How to Craft Backdoors with Unlabeled Data Alone?	Apr 10, 2024	Backdoor AttackSelf-Supervised Learning	CodeCode Available	5
Backdoor Graph Condensation	Jul 3, 2024	Backdoor Attack	CodeCode Available	5
Backdoor for Debias: Mitigating Model Bias with Backdoor Attack-based Artificial Bias	Mar 1, 2023	Backdoor AttackKnowledge Distillation	CodeCode Available	5
Genetic Algorithm-Based Dynamic Backdoor Attack on Federated Learning-Based Network Traffic Classification	Sep 27, 2023	Backdoor AttackFederated Learning	CodeCode Available	5

Show:10 25 50

← PrevPage 14 of 53Next →

No leaderboard results yet.