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 411–420 of 492 papers

TitleStatusHype
Data Poisoning Attacks Against Federated Learning SystemsCode1
Odyssey: Creation, Analysis and Detection of Trojan ModelsCode0
Mitigating backdoor attacks in LSTM-based Text Classification Systems by Backdoor Keyword Identification—0
You Autocomplete Me: Poisoning Vulnerabilities in Neural Code Completion—0
Subpopulation Data Poisoning AttacksCode0
Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning AttacksCode1
On Adversarial Bias and the Robustness of Fair Machine LearningCode0
Robust Variational Autoencoder for Tabular Data with Beta Divergence—0
Auditing Differentially Private Machine Learning: How Private is Private SGD?Code1
Online Data Poisoning Attacks—0
Show:102550
← PrevPage 42 of 50Next →

No leaderboard results yet.