SOTAVerified

Data Poisoning

Data Poisoning is an adversarial attack that tries to manipulate the training dataset in order to control the prediction behavior of a trained model such that the model will label malicious examples into a desired classes (e.g., labeling spam e-mails as safe).

Source: Explaining Vulnerabilities to Adversarial Machine Learning through Visual Analytics

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 321–330 of 492 papers

TitleStatusHype
Winter Soldier: Backdooring Language Models at Pre-Training with Indirect Data Poisoning—0
Wolf in Sheep's Clothing - The Downscaling Attack Against Deep Learning Applications—0
You Autocomplete Me: Poisoning Vulnerabilities in Neural Code Completion—0
Derivative-free Alternating Projection Algorithms for General Nonconvex-Concave Minimax Problems—0
Model Hijacking Attack in Federated Learning—0
Mitigating Malicious Attacks in Federated Learning via Confidence-aware Defense—0
Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection—0
TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks—0
A Backdoor Approach with Inverted Labels Using Dirty Label-Flipping Attacks—0
A Bayesian Incentive Mechanism for Poison-Resilient Federated Learning—0
Show:102550
← PrevPage 33 of 50Next →

No leaderboard results yet.