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 1–25 of 492 papers

TitleStatusHype
A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future TrendsCode4
Safety at Scale: A Comprehensive Survey of Large Model SafetyCode3
BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language ModelsCode3
Data Poisoning in LLMs: Jailbreak-Tuning and Scaling LawsCode3
Quantifying the robustness of deep multispectral segmentation models against natural perturbations and data poisoningCode3
SoK: Benchmarking Poisoning Attacks and Defenses in Federated LearningCode2
Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based AgentsCode2
Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language ModelsCode2
Backdoor Learning: A SurveyCode2
VLMs Can Aggregate Scattered Training PatchesCode1
Data Poisoning in Deep Learning: A SurveyCode1
BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense EvaluationCode1
PoisonBench: Assessing Large Language Model Vulnerability to Data PoisoningCode1
Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew ResilienceCode1
PureGen: Universal Data Purification for Train-Time Poison Defense via Generative Model DynamicsCode1
PureEBM: Universal Poison Purification via Mid-Run Dynamics of Energy-Based ModelsCode1
Optimistic Verifiable Training by Controlling Hardware NondeterminismCode1
Learning to Poison Large Language Models for Downstream ManipulationCode1
Data Poisoning based Backdoor Attacks to Contrastive LearningCode1
FlowMur: A Stealthy and Practical Audio Backdoor Attack with Limited KnowledgeCode1
IMMA: Immunizing text-to-image Models against Malicious AdaptationCode1
Vulnerabilities in AI Code Generators: Exploring Targeted Data Poisoning AttacksCode1
FedDefender: Backdoor Attack Defense in Federated LearningCode1
On the Exploitability of Instruction TuningCode1
DeepfakeArt Challenge: A Benchmark Dataset for Generative AI Art Forgery and Data Poisoning DetectionCode1
Show:102550
← PrevPage 1 of 20Next →

No leaderboard results yet.