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 91–100 of 523 papers

Title	Date	Tasks	Status	Hype	Score
LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning	Mar 25, 2024	Backdoor Attack	CodeCode Available	1	5
Backdoor Defense via Deconfounded Representation Learning	Mar 13, 2023	Backdoor Attackbackdoor defense	CodeCode Available	1	5
Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification	Dec 21, 2020	Adversarial AttackBackdoor Attack	CodeCode Available	1	5
Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transformers	May 17, 2024	AllBackdoor Attack	CodeCode Available	1	5
An Embarrassingly Simple Backdoor Attack on Self-supervised Learning	Oct 13, 2022	Adversarial RobustnessBackdoor Attack	CodeCode Available	1	5
Few-Shot Backdoor Attacks on Visual Object Tracking	Jan 31, 2022	Autonomous DrivingBackdoor Attack	CodeCode Available	1	5
PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models	Oct 19, 2023	Backdoor Attack	CodeCode Available	1	5
Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases	Jul 31, 2020	Backdoor Attack	CodeCode Available	1	5
Embedding and Extraction of Knowledge in Tree Ensemble Classifiers	Oct 16, 2020	Backdoor AttackBIG-bench Machine Learning	CodeCode Available	1	5
Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection	Feb 18, 2024	Backdoor Attack	CodeCode Available	1	5

Show:10 25 50

← PrevPage 10 of 53Next →

No leaderboard results yet.