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 101–125 of 523 papers

Title	Date	Tasks	Status	Hype
ONION: A Simple and Effective Defense Against Textual Backdoor Attacks	Nov 20, 2020	Backdoor Attackbackdoor defense	CodeCode Available	1
Backdoor Attack against Speaker Verification	Oct 22, 2020	Backdoor AttackClustering	CodeCode Available	1
Input-Aware Dynamic Backdoor Attack	Oct 16, 2020	Backdoor AttackDiversity	CodeCode Available	1
Embedding and Extraction of Knowledge in Tree Ensemble Classifiers	Oct 16, 2020	Backdoor AttackBIG-bench Machine Learning	CodeCode Available	1
Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases	Jul 31, 2020	Backdoor Attack	CodeCode Available	1
Defending against Backdoors in Federated Learning with Robust Learning Rate	Jul 7, 2020	Backdoor AttackFederated Learning	CodeCode Available	1
Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks	Jul 5, 2020	Backdoor Attack	CodeCode Available	1
Can We Mitigate Backdoor Attack Using Adversarial Detection Methods?	Jun 26, 2020	Adversarial DefenseBackdoor Attack	CodeCode Available	1
Graph Backdoor	Jun 21, 2020	Backdoor AttackDescriptive	CodeCode Available	1
Backdoor Attacks to Graph Neural Networks	Jun 19, 2020	Backdoor AttackGeneral Classification	CodeCode Available	1
DBA: Distributed Backdoor Attacks against Federated Learning	May 1, 2020	Backdoor AttackFeature Importance	CodeCode Available	1
Clean-Label Backdoor Attacks on Video Recognition Models	Mar 6, 2020	Backdoor Attackbackdoor defense	CodeCode Available	1
Hidden Trigger Backdoor Attacks	Sep 30, 2019	Backdoor Attackimage-classification	CodeCode Available	1
A new Backdoor Attack in CNNs by training set corruption without label poisoning	Feb 12, 2019	Backdoor AttackGeneral Classification	CodeCode Available	1
VisualTrap: A Stealthy Backdoor Attack on GUI Agents via Visual Grounding Manipulation	Jul 9, 2025	Backdoor AttackVisual Grounding	—Unverified	0
Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning	Jul 7, 2025	Backdoor AttackDeep Reinforcement Learning	—Unverified	0
CUBA: Controlled Untargeted Backdoor Attack against Deep Neural Networks	Jun 20, 2025	Backdoor Attackbackdoor defense	—Unverified	0
Screen Hijack: Visual Poisoning of VLM Agents in Mobile Environments	Jun 16, 2025	Backdoor Attack	—Unverified	0
ME: Trigger Element Combination Backdoor Attack on Copyright Infringement	Jun 12, 2025	Backdoor Attack	—Unverified	0
Single-Node Trigger Backdoor Attacks in Graph-Based Recommendation Systems	Jun 10, 2025	Backdoor AttackRecommendation Systems	—Unverified	0
SPBA: Utilizing Speech Large Language Model for Backdoor Attacks on Speech Classification Models	Jun 10, 2025	Backdoor AttackKeyword Spotting	—Unverified	0
Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation	Jun 8, 2025	Backdoor AttackData Poisoning	—Unverified	0
Invisible Backdoor Triggers in Image Editing Model via Deep Watermarking	Jun 5, 2025	Backdoor AttackImage Generation	CodeCode Available	0
Heterogeneous Graph Backdoor Attack	May 30, 2025	Backdoor Attackbackdoor defense	—Unverified	0
Poison in the Well: Feature Embedding Disruption in Backdoor Attacks	May 26, 2025	Backdoor Attack	—Unverified	0

Show:10 25 50

← PrevPage 5 of 21Next →

No leaderboard results yet.