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
Game-Theoretic Unlearnable Example GeneratorCode0
Fooling Partial Dependence via Data PoisoningCode0
From Shortcuts to Triggers: Backdoor Defense with Denoised PoECode0
Federated Learning Under Attack: Exposing Vulnerabilities through Data Poisoning Attacks in Computer NetworksCode0
From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion ModelsCode0
HINT: Healthy Influential-Noise based Training to Defend against Data Poisoning AttacksCode0
Backdoor Attack is a Devil in Federated GAN-based Medical Image SynthesisCode0
Explainable Data Poison Attacks on Human Emotion Evaluation Systems based on EEG SignalsCode0
An Equivalence Between Data Poisoning and Byzantine Gradient AttacksCode0
Explaining Vulnerabilities to Adversarial Machine Learning through Visual AnalyticsCode0
Show:102550
← PrevPage 12 of 50Next →

No leaderboard results yet.