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 221–230 of 492 papers

TitleStatusHype
Pick your Poison: Undetectability versus Robustness in Data Poisoning Attacks—0
Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data PoisoningCode1
Beyond the Model: Data Pre-processing Attack to Deep Learning Models in Android Apps—0
Interactive System-wise Anomaly Detection—0
INK: Inheritable Natural Backdoor Attack Against Model Distillation—0
Defending Against Patch-based Backdoor Attacks on Self-Supervised LearningCode1
Mole Recruitment: Poisoning of Image Classifiers via Selective Batch SamplingCode0
Denoising Autoencoder-based Defensive Distillation as an Adversarial Robustness Algorithm—0
Learning the Unlearnable: Adversarial Augmentations Suppress Unlearnable Example AttacksCode1
PORE: Provably Robust Recommender Systems against Data Poisoning AttacksCode0
Show:102550
← PrevPage 23 of 50Next →

No leaderboard results yet.