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 101–110 of 492 papers

TitleStatusHype
Concealed Data Poisoning Attacks on NLP Models—0
Certified Robustness to Label-Flipping Attacks via Randomized Smoothing—0
Class Machine Unlearning for Complex Data via Concepts Inference and Data Poisoning—0
Adversarial Learning in Statistical Classification: A Comprehensive Review of Defenses Against Attacks—0
Clean Image May be Dangerous: Data Poisoning Attacks Against Deep Hashing—0
Clean Label Attacks against SLU Systems—0
Cut the Deadwood Out: Post-Training Model Purification with Selective Module Substitution—0
CLEAR: Clean-Up Sample-Targeted Backdoor in Neural Networks—0
Certified Robustness to Adversarial Label-Flipping Attacks via Randomized Smoothing—0
Certified Robustness of Nearest Neighbors against Data Poisoning and Backdoor Attacks—0
Show:102550
← PrevPage 11 of 50Next →

No leaderboard results yet.