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 426–450 of 523 papers

Title	Date	Tasks	Status	Hype
Backdoor Attack with Imperceptible Input and Latent Modification	Dec 1, 2021	Backdoor Attack	—Unverified	0
Anomaly Localization in Model Gradients Under Backdoor Attacks Against Federated Learning	Nov 29, 2021	Anomaly LocalizationBackdoor Attack	CodeCode Available	0
Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks	Nov 25, 2021	AttributeBackdoor Attack	CodeCode Available	1
DBIA: Data-free Backdoor Injection Attack against Transformer Networks	Nov 22, 2021	Backdoor Attackimage-classification	CodeCode Available	0
Backdoor Attack through Frequency Domain	Nov 22, 2021	Autonomous DrivingBackdoor Attack	CodeCode Available	0
An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defences	Nov 16, 2021	Backdoor Attack	—Unverified	0
Triggerless Backdoor Attack for NLP Tasks with Clean Labels	Nov 15, 2021	Backdoor AttackSentence	CodeCode Available	1
Enhancing Backdoor Attacks with Multi-Level MMD Regularization	Nov 9, 2021	Backdoor Attack	CodeCode Available	0
Backdoor Pre-trained Models Can Transfer to All	Oct 30, 2021	AllBackdoor Attack	CodeCode Available	0
Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomes	Oct 26, 2021	Backdoor AttackFederated Learning	CodeCode Available	1
Anti-Distillation Backdoor Attacks: Backdoors Can Really Survive in Knowledge Distillation	Oct 24, 2021	Backdoor AttackKnowledge Distillation	CodeCode Available	1
Anti-Backdoor Learning: Training Clean Models on Poisoned Data	Oct 22, 2021	Backdoor Attack	CodeCode Available	1
Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer	Oct 14, 2021	Adversarial AttackBackdoor Attack	CodeCode Available	1
Widen The Backdoor To Let More Attackers In	Oct 9, 2021	Backdoor Attack	—Unverified	0
Dyn-Backdoor: Backdoor Attack on Dynamic Link Prediction	Oct 8, 2021	Backdoor AttackDynamic Link Prediction	—Unverified	0
BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models	Oct 6, 2021	Backdoor AttackTransfer Learning	—Unverified	0
Defending Against Backdoor Attacks Using Ensembles of Weak Learners	Sep 29, 2021	Backdoor AttackData Poisoning	—Unverified	0
Feature Grinding: Efficient Backdoor Sanitation in Deep Neural Networks	Sep 29, 2021	Backdoor Attack	—Unverified	0
Gradient Broadcast Adaptation: Defending against the backdoor attack in pre-trained models	Sep 29, 2021	Backdoor Attacktext-classification	—Unverified	0
MARNET: Backdoor Attacks against Value-Decomposition Multi-Agent Reinforcement Learning	Sep 29, 2021	Backdoor AttackDeep Reinforcement Learning	—Unverified	0
Defending Backdoor Data Poisoning Attacks by Using Noisy Label Defense Algorithm	Sep 29, 2021	Backdoor AttackData Poisoning	—Unverified	0
FooBaR: Fault Fooling Backdoor Attack on Neural Network Training	Sep 23, 2021	Backdoor Attackimage-classification	CodeCode Available	0
BFClass: A Backdoor-free Text Classification Framework	Sep 22, 2021	Backdoor AttackClassification	—Unverified	0
Backdoor Attacks on Federated Learning with Lottery Ticket Hypothesis	Sep 22, 2021	Backdoor AttackFederated Learning	CodeCode Available	1
Backdoor Attack on Hash-based Image Retrieval via Clean-label Data Poisoning	Sep 18, 2021	Backdoor AttackData Poisoning	CodeCode Available	1

Show:10 25 50

← PrevPage 18 of 21Next →

No leaderboard results yet.