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 361–370 of 492 papers

TitleStatusHype
Certifiers Make Neural Networks Vulnerable to Availability Attacks—0
ABC-FL: Anomalous and Benign client Classification in Federated Learning—0
Classification Auto-Encoder based Detector against Diverse Data Poisoning AttacksCode0
Adversarial Attacks Against Deep Reinforcement Learning Framework in Internet of Vehicles—0
Derivative-free Alternating Projection Algorithms for General Nonconvex-Concave Minimax Problems—0
Putting words into the system’s mouth: A targeted attack on neural machine translation using monolingual data poisoningCode0
Fairness-aware Summarization for Justified Decision-Making—0
Putting words into the system's mouth: A targeted attack on neural machine translation using monolingual data poisoningCode0
Understanding the Limits of Unsupervised Domain Adaptation via Data PoisoningCode0
Poisoning Attack against Estimating from Pairwise ComparisonsCode0
Show:102550
← PrevPage 37 of 50Next →

No leaderboard results yet.