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 11–20 of 492 papers

TitleStatusHype
Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation—0
Securing Traffic Sign Recognition Systems in Autonomous Vehicles—0
VLMs Can Aggregate Scattered Training PatchesCode1
Adversarial Threat Vectors and Risk Mitigation for Retrieval-Augmented Generation Systems—0
Cascading Adversarial Bias from Injection to Distillation in Language Models—0
Distributed Federated Learning for Vehicular Network Security: Anomaly Detection Benefits and Multi-Domain Attack Threats—0
Are Time-Series Foundation Models Deployment-Ready? A Systematic Study of Adversarial Robustness Across Domains—0
Security Concerns for Large Language Models: A Survey—0
Backdoors in DRL: Four Environments Focusing on In-distribution Triggers—0
A Linear Approach to Data Poisoning—0
Show:102550
← PrevPage 2 of 50Next →

No leaderboard results yet.