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 351–360 of 492 papers

TitleStatusHype
On the Effectiveness of Poisoning against Unsupervised Domain Adaptation—0
Poisoning Deep Reinforcement Learning Agents with In-Distribution Triggers—0
Gradient-based Data Subversion Attack Against Binary Classifiers—0
A BIC-based Mixture Model Defense against Data Poisoning Attacks on Classifiers—0
A Gradient Method for Multilevel Optimization—0
Fooling Partial Dependence via Data PoisoningCode0
De-Pois: An Attack-Agnostic Defense against Data Poisoning Attacks—0
Incompatibility Clustering as a Defense Against Backdoor Poisoning AttacksCode0
Influence Based Defense Against Data Poisoning Attacks in Online Learning—0
FedCom: A Byzantine-Robust Local Model Aggregation Rule Using Data Commitment for Federated Learning—0
Show:102550
← PrevPage 36 of 50Next →

No leaderboard results yet.