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 91–100 of 492 papers

TitleStatusHype
Concealing Backdoor Model Updates in Federated Learning by Trigger-Optimized Data Poisoning—0
Attacks on the neural network and defense methods—0
Adversarial Poisoning Attacks and Defense for General Multi-Class Models Based On Synthetic Reduced Nearest Neighbors—0
Attacks against Abstractive Text Summarization Models through Lead Bias and Influence Functions—0
Adversarial Data Poisoning Attacks on Quantum Machine Learning in the NISQ Era—0
Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection—0
Model Hijacking Attack in Federated Learning—0
Atlas: A Framework for ML Lifecycle Provenance & Transparency—0
Adversarial Learning in Statistical Classification: A Comprehensive Review of Defenses Against Attacks—0
Certified Robustness to Adversarial Label-Flipping Attacks via Randomized Smoothing—0
Show:102550
← PrevPage 10 of 50Next →

No leaderboard results yet.