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 211–220 of 492 papers

TitleStatusHype
Chameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning—0
FLock: Defending Malicious Behaviors in Federated Learning with Blockchain—0
Fed-Credit: Robust Federated Learning with Credibility Management—0
FocusedCleaner: Sanitizing Poisoned Graphs for Robust GNN-based Node Classification—0
FedCom: A Byzantine-Robust Local Model Aggregation Rule Using Data Commitment for Federated Learning—0
FedBayes: A Zero-Trust Federated Learning Aggregation to Defend Against Adversarial Attacks—0
Fortifying Federated Learning Towards Trustworthiness via Auditable Data Valuation and Verifiable Client Contribution—0
Fragile Giants: Understanding the Susceptibility of Models to Subpopulation Attacks—0
Certified Robustness to Label-Flipping Attacks via Randomized Smoothing—0
Atlas: A Framework for ML Lifecycle Provenance & Transparency—0
Show:102550
← PrevPage 22 of 50Next →

No leaderboard results yet.