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 121–130 of 492 papers

TitleStatusHype
Federated Learning Under Attack: Exposing Vulnerabilities through Data Poisoning Attacks in Computer NetworksCode0
Poison-RAG: Adversarial Data Poisoning Attacks on Retrieval-Augmented Generation in Recommender SystemsCode0
Explainable Data Poison Attacks on Human Emotion Evaluation Systems based on EEG SignalsCode0
Incompatibility Clustering as a Defense Against Backdoor Poisoning AttacksCode0
Explaining Vulnerabilities to Adversarial Machine Learning through Visual AnalyticsCode0
Exacerbating Algorithmic Bias through Fairness AttacksCode0
Excess Capacity and Backdoor PoisoningCode0
Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning AttacksCode0
Fooling Partial Dependence via Data PoisoningCode0
Indiscriminate Data Poisoning Attacks on Neural NetworksCode0
Show:102550
← PrevPage 13 of 50Next →

No leaderboard results yet.