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
Analyzing the Robustness of Decentralized Horizontal and Vertical Federated Learning Architectures in a Non-IID Scenario—0
Analyzing the vulnerabilities in SplitFed Learning: Assessing the robustness against Data Poisoning Attacks—0
An Investigation of Data Poisoning Defenses for Online Learning—0
An Optimal Control View of Adversarial Machine Learning—0
A Novel Pearson Correlation-Based Merging Algorithm for Robust Distributed Machine Learning with Heterogeneous Data—0
Approaching the Harm of Gradient Attacks While Only Flipping Labels—0
Are Time-Series Foundation Models Deployment-Ready? A Systematic Study of Adversarial Robustness Across Domains—0
A Robust Attack: Displacement Backdoor Attack—0
Provable Training of a ReLU Gate with an Iterative Non-Gradient Algorithm—0
Atlas: A Framework for ML Lifecycle Provenance & Transparency—0
Show:102550
← PrevPage 36 of 50Next →

No leaderboard results yet.