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
Spectral Signatures in Backdoor AttacksCode0
A Mixture Model Based Defense for Data Poisoning Attacks Against Naive Bayes Spam Filters—0
Data Poisoning Attack against Unsupervised Node Embedding Methods—0
Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbation—0
Data Poisoning Attacks against Online Learning—0
Data Poisoning Attacks in Contextual Bandits—0
How To Backdoor Federated LearningCode1
Is feature selection secure against training data poisoning?—0
Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural NetworksCode1
Label Sanitization against Label Flipping Poisoning Attacks—0
Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe NoiseCode0
Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly DetectionCode0
Wolf in Sheep's Clothing - The Downscaling Attack Against Deep Learning Applications—0
Targeted Backdoor Attacks on Deep Learning Systems Using Data PoisoningCode0
Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization—0
Certified Defenses for Data Poisoning AttacksCode0
Data Poisoning Attacks on Factorization-Based Collaborative Filtering—0
Show:102550
← PrevPage 20 of 20Next →

No leaderboard results yet.