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 221–230 of 492 papers

TitleStatusHype
Atlas: A Framework for ML Lifecycle Provenance & Transparency—0
Fairness-aware Summarization for Justified Decision-Making—0
Certified Robustness to Adversarial Label-Flipping Attacks via Randomized Smoothing—0
Face Recognition in the age of CLIP & Billion image datasets—0
Exploring Vulnerabilities and Protections in Large Language Models: A Survey—0
Certified Robustness of Nearest Neighbors against Data Poisoning and Backdoor Attacks—0
Provable Training of a ReLU Gate with an Iterative Non-Gradient Algorithm—0
Generating Fake Cyber Threat Intelligence Using Transformer-Based Models—0
Generative AI in Cybersecurity: A Comprehensive Review of LLM Applications and Vulnerabilities—0
Explainable Label-flipping Attacks on Human Emotion Assessment System—0
Show:102550
← PrevPage 23 of 50Next →

No leaderboard results yet.