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 61–70 of 492 papers

TitleStatusHype
A Distributed Trust Framework for Privacy-Preserving Machine LearningCode1
Backdoor Attacks on Crowd CountingCode1
Black-Box Attacks on Sequential Recommenders via Data-Free Model ExtractionCode1
Backdoor Attack on Hash-based Image Retrieval via Clean-label Data PoisoningCode1
Data Poisoning based Backdoor Attacks to Contrastive LearningCode1
Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew ResilienceCode1
BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense EvaluationCode1
PureEBM: Universal Poison Purification via Mid-Run Dynamics of Energy-Based ModelsCode1
Data Poisoning Attacks Against Federated Learning SystemsCode1
Learning the Unlearnable: Adversarial Augmentations Suppress Unlearnable Example AttacksCode1
Show:102550
← PrevPage 7 of 50Next →

No leaderboard results yet.