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 391–400 of 492 papers

TitleStatusHype
Adversarial Poisoning Attacks and Defense for General Multi-Class Models Based On Synthetic Reduced Nearest Neighbors—0
Generating Fake Cyber Threat Intelligence Using Transformer-Based Models—0
Property Inference From Poisoning—0
Adversarial Vulnerability of Active Transfer Learning—0
Data Poisoning Attacks to Deep Learning Based Recommender Systems—0
Just How Toxic is Data Poisoning? A Benchmark for Backdoor and Data Poisoning Attacks—0
CLEAR: Clean-Up Sample-Targeted Backdoor in Neural Networks—0
Sself: Robust Federated Learning against Stragglers and Adversaries—0
Active Learning Under Malicious Mislabeling and Poisoning Attacks—0
Federated Unlearning—0
Show:102550
← PrevPage 40 of 50Next →

No leaderboard results yet.