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 276–300 of 492 papers

TitleStatusHype
Evaluating Impact of User-Cluster Targeted Attacks in Matrix Factorisation Recommenders—0
Pick your Poison: Undetectability versus Robustness in Data Poisoning Attacks—0
Beyond the Model: Data Pre-processing Attack to Deep Learning Models in Android Apps—0
Interactive System-wise Anomaly Detection—0
INK: Inheritable Natural Backdoor Attack Against Model Distillation—0
Mole Recruitment: Poisoning of Image Classifiers via Selective Batch SamplingCode0
Denoising Autoencoder-based Defensive Distillation as an Adversarial Robustness Algorithm—0
PORE: Provably Robust Recommender Systems against Data Poisoning AttacksCode0
Recursive Euclidean Distance Based Robust Aggregation Technique For Federated Learning—0
Naive Bayes Classifiers over Missing Data: Decision and PoisoningCode0
Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning AttacksCode0
WW-FL: Secure and Private Large-Scale Federated Learning—0
QTrojan: A Circuit Backdoor Against Quantum Neural Networks—0
Explainable Label-flipping Attacks on Human Emotion Assessment System—0
Training-free Lexical Backdoor Attacks on Language ModelsCode0
Data Poisoning Attacks on EEG Signal-based Risk Assessment Systems—0
Temporal Robustness against Data Poisoning—0
Run-Off Election: Improved Provable Defense against Data Poisoning AttacksCode0
CATFL: Certificateless Authentication-based Trustworthy Federated Learning for 6G Semantic Communications—0
Face Recognition in the age of CLIP & Billion image datasets—0
Explainable Data Poison Attacks on Human Emotion Evaluation Systems based on EEG SignalsCode0
Federated Transfer-Ordered-Personalized Learning for Driver Monitoring Application—0
Computation and Data Efficient Backdoor Attacks—0
Defending Against Disinformation Attacks in Open-Domain Question AnsweringCode0
Pre-trained Encoders in Self-Supervised Learning Improve Secure and Privacy-preserving Supervised Learning—0
Show:102550
← PrevPage 12 of 20Next →

No leaderboard results yet.