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 126–150 of 492 papers

TitleStatusHype
HINT: Healthy Influential-Noise based Training to Defend against Data Poisoning AttacksCode0
Improved Certified Defenses against Data Poisoning with (Deterministic) Finite AggregationCode0
On Adversarial Bias and the Robustness of Fair Machine LearningCode0
Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor AttacksCode0
Analysis and Detectability of Offline Data Poisoning Attacks on Linear Dynamical SystemsCode0
FullCert: Deterministic End-to-End Certification for Training and Inference of Neural NetworksCode0
From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion ModelsCode0
Game-Theoretic Unlearnable Example GeneratorCode0
Fooling Partial Dependence via Data PoisoningCode0
2D-OOB: Attributing Data Contribution Through Joint Valuation FrameworkCode0
Federated Learning Under Attack: Exposing Vulnerabilities through Data Poisoning Attacks in Computer NetworksCode0
Generalization Bound and New Algorithm for Clean-Label Backdoor AttackCode0
Depth-2 Neural Networks Under a Data-Poisoning AttackCode0
Explaining Vulnerabilities to Adversarial Machine Learning through Visual AnalyticsCode0
Excess Capacity and Backdoor PoisoningCode0
Exacerbating Algorithmic Bias through Fairness AttacksCode0
Explainable Data Poison Attacks on Human Emotion Evaluation Systems based on EEG SignalsCode0
Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning AttacksCode0
DROP: Poison Dilution via Knowledge Distillation for Federated LearningCode0
BagFlip: A Certified Defense against Data PoisoningCode0
Efficient Reward Poisoning Attacks on Online Deep Reinforcement LearningCode0
From Shortcuts to Triggers: Backdoor Defense with Denoised PoECode0
Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly DetectionCode0
Differentially-Private Decision Trees and Provable Robustness to Data PoisoningCode0
Delta-Influence: Unlearning Poisons via Influence FunctionsCode0
Show:102550
← PrevPage 6 of 20Next →

No leaderboard results yet.