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 441–450 of 492 papers

TitleStatusHype
Certified Robustness to Label-Flipping Attacks via Randomized Smoothing—0
Can't Boil This Frog: Robustness of Online-Trained Autoencoder-Based Anomaly Detectors to Adversarial Poisoning Attacks—0
Regularization Helps with Mitigating Poisoning Attacks: Distributionally-Robust Machine Learning Using the Wasserstein Distance—0
Humpty Dumpty: Controlling Word Meanings via Corpus Poisoning—0
Deep Probabilistic Models to Detect Data Poisoning Attacks—0
Proving Data-Poisoning Robustness in Decision Trees—0
Data Poisoning Attacks on Neighborhood-based Recommender Systems—0
Local Model Poisoning Attacks to Byzantine-Robust Federated Learning—0
Revealing Perceptible Backdoors, without the Training Set, via the Maximum Achievable Misclassification Fraction Statistic—0
A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learning—0
Show:102550
← PrevPage 45 of 50Next →

No leaderboard results yet.