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 451–475 of 523 papers

Title	Date	Tasks	Status	Hype
Check Your Other Door! Creating Backdoor Attacks in the Frequency Domain	Sep 12, 2021	Backdoor Attackimage-classification	—Unverified	0
Backdoor Attack and Defense for Deep Regression	Sep 6, 2021	Backdoor Attackbackdoor defense	—Unverified	0
Excess Capacity and Backdoor Poisoning	Sep 2, 2021	Adversarial AttackBackdoor Attack	CodeCode Available	0
Poison Ink: Robust and Invisible Backdoor Attack	Aug 5, 2021	Adversarial AttackBackdoor Attack	CodeCode Available	1
Rethinking Stealthiness of Backdoor Attack against NLP Models	Aug 1, 2021	Backdoor AttackData Augmentation	CodeCode Available	1
BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning	Aug 1, 2021	Backdoor AttackSelf-Supervised Learning	CodeCode Available	1
Can You Hear It? Backdoor Attacks via Ultrasonic Triggers	Jul 30, 2021	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	—Unverified	0
Subnet Replacement: Deployment-stage backdoor attack against deep neural networks in gray-box setting	Jul 15, 2021	Backdoor AttackPhilosophy	—Unverified	0
BadNL: Backdoor Attacks Against NLP Models	Jun 18, 2021	Backdoor AttackSentence	—Unverified	0
Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch	Jun 16, 2021	Backdoor Attack	CodeCode Available	1
Handcrafted Backdoors in Deep Neural Networks	Jun 8, 2021	Backdoor Attack	—Unverified	0
Defending Against Backdoor Attacks in Natural Language Generation	Jun 3, 2021	Backdoor AttackDialogue Generation	CodeCode Available	1
Detecting Backdoor in Deep Neural Networks via Intentional Adversarial Perturbations	May 29, 2021	Backdoor Attack	—Unverified	0
Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger	May 26, 2021	Backdoor Attack	CodeCode Available	1
Backdoor Attacks on Self-Supervised Learning	May 21, 2021	Backdoor AttackInductive Bias	CodeCode Available	1
Poisoning MorphNet for Clean-Label Backdoor Attack to Point Clouds	May 11, 2021	Adversarial AttackBackdoor Attack	—Unverified	0
BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning	May 2, 2021	Atari GamesBackdoor Attack	—Unverified	0
A Master Key Backdoor for Universal Impersonation Attack against DNN-based Face Verification	May 1, 2021	Backdoor AttackFace Verification	—Unverified	0
Stealthy Backdoors as Compression Artifacts	Apr 30, 2021	Backdoor AttackModel Compression	CodeCode Available	0
Robust Backdoor Attacks against Deep Neural Networks in Real Physical World	Apr 15, 2021	Backdoor AttackFace Recognition	—Unverified	0
Explainability-based Backdoor Attacks Against Graph Neural Networks	Apr 8, 2021	Backdoor AttackNode Classification	—Unverified	0
Backdoor Attack in the Physical World	Apr 6, 2021	Backdoor Attack	—Unverified	0
PointBA: Towards Backdoor Attacks in 3D Point Cloud	Mar 30, 2021	Backdoor AttackDisentanglement	—Unverified	0
Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models	Mar 29, 2021	Backdoor AttackData Poisoning	CodeCode Available	1
EX-RAY: Distinguishing Injected Backdoor from Natural Features in Neural Networks by Examining Differential Feature Symmetry	Mar 16, 2021	Backdoor Attack	—Unverified	0

Show:10 25 50

← PrevPage 19 of 21Next →

No leaderboard results yet.