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 261–270 of 492 papers

TitleStatusHype
Review-Incorporated Model-Agnostic Profile Injection Attacks on Recommender Systems—0
Robust Federated Training via Collaborative Machine Teaching using Trusted Instances—0
Robust learning under clean-label attack—0
Robustly-reliable learners under poisoning attacks—0
Robust Variational Autoencoder for Tabular Data with Beta Divergence—0
SAFELOC: Overcoming Data Poisoning Attacks in Heterogeneous Federated Machine Learning for Indoor Localization—0
SafeNet: The Unreasonable Effectiveness of Ensembles in Private Collaborative Learning—0
Saving Stochastic Bandits from Poisoning Attacks via Limited Data Verification—0
Securing Traffic Sign Recognition Systems in Autonomous Vehicles—0
Security and Privacy Challenges in Deep Learning Models—0
Show:102550
← PrevPage 27 of 50Next →

No leaderboard results yet.