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 361–370 of 492 papers

TitleStatusHype
ML Attack Models: Adversarial Attacks and Data Poisoning Attacks—0
How to Backdoor HyperNetwork in Personalized Federated Learning?—0
Multi-Trigger Poisoning Amplifies Backdoor Vulnerabilities in LLMs—0
Privacy and Copyright Protection in Generative AI: A Lifecycle Perspective—0
Neural network fragile watermarking with no model performance degradation—0
Neuromimetic metaplasticity for adaptive continual learning—0
No, of course I can! Refusal Mechanisms Can Be Exploited Using Harmless Fine-Tuning Data—0
Reclaiming "Open AI" -- AI Model Serving Can Be Open Access, Yet Monetizable and Loyal—0
On Defending Against Label Flipping Attacks on Malware Detection Systems—0
One Pixel is All I Need—0
Show:102550
← PrevPage 37 of 50Next →

No leaderboard results yet.