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 231–240 of 492 papers

TitleStatusHype
Bait and Switch: Online Training Data Poisoning of Autonomous Driving Systems—0
GFCL: A GRU-based Federated Continual Learning Framework against Data Poisoning Attacks in IoV—0
A Mixture Model Based Defense for Data Poisoning Attacks Against Naive Bayes Spam Filters—0
Gradient-based Data Subversion Attack Against Binary Classifiers—0
Concealed Data Poisoning Attacks on NLP Models—0
Hard Work Does Not Always Pay Off: Poisoning Attacks on Neural Architecture Search—0
Have You Poisoned My Data? Defending Neural Networks against Data Poisoning—0
Data Shifts Hurt CoT: A Theoretical Study—0
CyberForce: A Federated Reinforcement Learning Framework for Malware Mitigation—0
Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses—0
Show:102550
← PrevPage 24 of 50Next →

No leaderboard results yet.