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 391–400 of 492 papers

TitleStatusHype
PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models—0
Poisoning Attacks and Defenses on Artificial Intelligence: A Survey—0
Poisoning Attacks to Local Differential Privacy Protocols for Trajectory Data—0
Poisoning Deep Reinforcement Learning Agents with In-Distribution Triggers—0
Poisoning Programs by Un-Repairing Code: Security Concerns of AI-generated Code—0
Policy Teaching via Data Poisoning in Learning from Human Preferences—0
Post-Training Overfitting Mitigation in DNN Classifiers—0
Practical Data Poisoning Attack against Next-Item Recommendation—0
SLSGD: Secure and Efficient Distributed On-device Machine Learning—0
Practical Poisoning Attacks on Neural Networks—0
Show:102550
← PrevPage 40 of 50Next →

No leaderboard results yet.