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 201–210 of 492 papers

TitleStatusHype
Fed-Credit: Robust Federated Learning with Credibility Management—0
SEEP: Training Dynamics Grounds Latent Representation Search for Mitigating Backdoor Poisoning Attacks—0
Concealing Backdoor Model Updates in Federated Learning by Trigger-Optimized Data Poisoning—0
Hard Work Does Not Always Pay Off: Poisoning Attacks on Neural Architecture Search—0
On the Relevance of Byzantine Robust Optimization Against Data Poisoning—0
Dual Model Replacement:invisible Multi-target Backdoor Attack based on Federal Learning—0
Data Poisoning Attacks on Off-Policy Policy Evaluation Methods—0
Precision Guided Approach to Mitigate Data Poisoning Attacks in Federated Learning—0
Two Heads are Better than One: Nested PoE for Robust Defense Against Multi-BackdoorsCode0
A Backdoor Approach with Inverted Labels Using Dirty Label-Flipping Attacks—0
Show:102550
← PrevPage 21 of 50Next →

No leaderboard results yet.