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 241–250 of 492 papers

TitleStatusHype
Provably Reliable Conformal Prediction Sets in the Presence of Data Poisoning—0
Proving Data-Poisoning Robustness in Decision Trees—0
Purifying Large Language Models by Ensembling a Small Language Model—0
QTrojan: A Circuit Backdoor Against Quantum Neural Networks—0
Reaching Data Confidentiality and Model Accountability on the CalTrain—0
Recursive Euclidean Distance Based Robust Aggregation Technique For Federated Learning—0
Redactor: A Data-centric and Individualized Defense Against Inference Attacks—0
FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learning—0
Regularisation Can Mitigate Poisoning Attacks: A Novel Analysis Based on Multiobjective Bilevel Optimisation—0
Regularization Helps with Mitigating Poisoning Attacks: Distributionally-Robust Machine Learning Using the Wasserstein Distance—0
Show:102550
← PrevPage 25 of 50Next →

No leaderboard results yet.