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 461–470 of 492 papers

TitleStatusHype
Federated Learning with Dual Attention for Robust Modulation Classification under Attacks—0
Federated Multi-Armed Bandits Under Byzantine Attacks—0
Federated Transfer-Ordered-Personalized Learning for Driver Monitoring Application—0
Federated Unlearning—0
FedNIA: Noise-Induced Activation Analysis for Mitigating Data Poisoning in FL—0
FheFL: Fully Homomorphic Encryption Friendly Privacy-Preserving Federated Learning with Byzantine Users—0
Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning—0
FLock: Defending Malicious Behaviors in Federated Learning with Blockchain—0
FocusedCleaner: Sanitizing Poisoned Graphs for Robust GNN-based Node Classification—0
Forcing Generative Models to Degenerate Ones: The Power of Data Poisoning Attacks—0
Show:102550
← PrevPage 47 of 50Next →

No leaderboard results yet.