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 476–492 of 492 papers

TitleStatusHype
Certified Robustness to Data Poisoning in Gradient-Based TrainingCode0
Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate ModelsCode0
Excess Capacity and Backdoor PoisoningCode0
Adversarial Robustness of Deep Learning Models for Inland Water Body Segmentation from SAR ImagesCode0
Exacerbating Algorithmic Bias through Fairness AttacksCode0
Two Heads are Better than One: Nested PoE for Robust Defense Against Multi-BackdoorsCode0
Certified Defenses for Data Poisoning AttacksCode0
On the Robustness of Random Forest Against Untargeted Data Poisoning: An Ensemble-Based ApproachCode0
Addressing The Devastating Effects Of Single-Task Data Poisoning In Exemplar-Free Continual LearningCode0
Spectral Signatures in Backdoor AttacksCode0
Backdoor Attack is a Devil in Federated GAN-based Medical Image SynthesisCode0
Efficient Reward Poisoning Attacks on Online Deep Reinforcement LearningCode0
Towards Understanding Quality Challenges of the Federated Learning for Neural Networks: A First Look from the Lens of RobustnessCode0
Understanding the Limits of Unsupervised Domain Adaptation via Data PoisoningCode0
Universal Backdoor AttacksCode0
Deep k-NN Defense against Clean-label Data Poisoning AttacksCode0
Naive Bayes Classifiers over Missing Data: Decision and PoisoningCode0
Show:102550
← PrevPage 20 of 20Next →

No leaderboard results yet.