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 271–280 of 492 papers

TitleStatusHype
Security and Privacy Challenges of Large Language Models: A Survey—0
Security Concerns for Large Language Models: A Survey—0
Security of Distributed Machine Learning: A Game-Theoretic Approach to Design Secure DSVM—0
SEEP: Training Dynamics Grounds Latent Representation Search for Mitigating Backdoor Poisoning Attacks—0
Self-Adaptive and Robust Federated Spectrum Sensing without Benign Majority for Cellular Networks—0
Shapley Homology: Topological Analysis of Sample Influence for Neural Networks—0
SHFL: Secure Hierarchical Federated Learning Framework for Edge Networks—0
Silent Branding Attack: Trigger-free Data Poisoning Attack on Text-to-Image Diffusion Models—0
Sky of Unlearning (SoUL): Rewiring Federated Machine Unlearning via Selective Pruning—0
Sniper GMMs: Structured Gaussian mixtures poison ML on large n small p data with high efficacy—0
Show:102550
← PrevPage 28 of 50Next →

No leaderboard results yet.