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 111–120 of 492 papers

TitleStatusHype
Computation and Data Efficient Backdoor Attacks—0
Concealing Backdoor Model Updates in Federated Learning by Trigger-Optimized Data Poisoning—0
Certified Robustness of Nearest Neighbors against Data Poisoning and Backdoor Attacks—0
ControlNET: A Firewall for RAG-based LLM System—0
Provable Training of a ReLU Gate with an Iterative Non-Gradient Algorithm—0
A Robust Attack: Displacement Backdoor Attack—0
Concealed Data Poisoning Attacks on NLP Models—0
Cut the Deadwood Out: Post-Training Model Purification with Selective Module Substitution—0
CyberForce: A Federated Reinforcement Learning Framework for Malware Mitigation—0
A BIC-based Mixture Model Defense against Data Poisoning Attacks on Classifiers—0
Show:102550
← PrevPage 12 of 50Next →

No leaderboard results yet.