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 251–260 of 492 papers

TitleStatusHype
Regularized Robustly Reliable Learners and Instance Targeted Attacks—0
Reinforcement Learning For Data Poisoning on Graph Neural Networks—0
Releasing Malevolence from Benevolence: The Menace of Benign Data on Machine Unlearning—0
Reliable Poisoned Sample Detection against Backdoor Attacks Enhanced by Sharpness Aware Minimization—0
Reputation-Based Federated Learning Defense to Mitigate Threats in EEG Signal Classification—0
Rethinking Backdoor Data Poisoning Attacks in the Context of Semi-Supervised Learning—0
Revamping Federated Learning Security from a Defender's Perspective: A Unified Defense with Homomorphic Encrypted Data Space—0
Detection of Backdoors in Trained Classifiers Without Access to the Training Set—0
Revealing Perceptible Backdoors, without the Training Set, via the Maximum Achievable Misclassification Fraction Statistic—0
Reverse Engineering Imperceptible Backdoor Attacks on Deep Neural Networks for Detection and Training Set Cleansing—0
Show:102550
← PrevPage 26 of 50Next →

No leaderboard results yet.