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 51–100 of 492 papers

TitleStatusHype
DROP: Poison Dilution via Knowledge Distillation for Federated LearningCode0
Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning—0
Detection of Physiological Data Tampering Attacks with Quantum Machine Learning—0
SoK: Benchmarking Poisoning Attacks and Defenses in Federated LearningCode2
Safety at Scale: A Comprehensive Survey of Large Model SafetyCode3
TrojanTime: Backdoor Attacks on Time Series Classification—0
Provably effective detection of effective data poisoning attacks—0
Poison-RAG: Adversarial Data Poisoning Attacks on Retrieval-Augmented Generation in Recommender SystemsCode0
A Novel Pearson Correlation-Based Merging Algorithm for Robust Distributed Machine Learning with Heterogeneous Data—0
Fortifying Federated Learning Towards Trustworthiness via Auditable Data Valuation and Verifiable Client Contribution—0
Cut the Deadwood Out: Post-Training Model Purification with Selective Module Substitution—0
Attacks on the neural network and defense methods—0
Trading Devil RL: Backdoor attack via Stock market, Bayesian Optimization and Reinforcement Learning—0
From Vulnerabilities to Remediation: A Systematic Literature Review of LLMs in Code Security—0
One Pixel is All I Need—0
BiCert: A Bilinear Mixed Integer Programming Formulation for Precise Certified Bounds Against Data Poisoning Attacks—0
Deep Learning Model Security: Threats and Defenses—0
Learning to Forget using Hypernetworks—0
Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models—0
Adversarial Data Poisoning Attacks on Quantum Machine Learning in the NISQ Era—0
Delta-Influence: Unlearning Poisons via Influence FunctionsCode0
Reliable Poisoned Sample Detection against Backdoor Attacks Enhanced by Sharpness Aware Minimization—0
BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense EvaluationCode1
SAFELOC: Overcoming Data Poisoning Attacks in Heterogeneous Federated Machine Learning for Indoor Localization—0
Learning from Convolution-based Unlearnable DatasetsCode0
Reclaiming "Open AI" -- AI Model Serving Can Be Open Access, Yet Monetizable and Loyal—0
Learning and Unlearning of Fabricated Knowledge in Language Models—0
Inverting Gradient Attacks Makes Powerful Data Poisoning—0
Attacks against Abstractive Text Summarization Models through Lead Bias and Influence Functions—0
Regularized Robustly Reliable Learners and Instance Targeted Attacks—0
Provably Reliable Conformal Prediction Sets in the Presence of Data Poisoning—0
PoisonBench: Assessing Large Language Model Vulnerability to Data PoisoningCode1
Fragile Giants: Understanding the Susceptibility of Models to Subpopulation Attacks—0
Data Taggants: Dataset Ownership Verification via Harmless Targeted Data Poisoning—0
On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning—0
Empirical Perturbation Analysis of Linear System Solvers from a Data Poisoning Perspective—0
Survey of Security and Data Attacks on Machine Unlearning In Financial and E-Commerce—0
Data Poisoning-based Backdoor Attack Framework against Supervised Learning Rules of Spiking Neural Networks—0
UTrace: Poisoning Forensics for Private Collaborative Learning—0
SHFL: Secure Hierarchical Federated Learning Framework for Edge Networks—0
Clean Label Attacks against SLU Systems—0
Unleashing Worms and Extracting Data: Escalating the Outcome of Attacks against RAG-based Inference in Scale and Severity Using JailbreakingCode0
Context is the Key: Backdoor Attacks for In-Context Learning with Vision Transformers—0
Blockchain-based Federated Recommendation with Incentive Mechanism—0
Protecting against simultaneous data poisoning attacks—0
BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language ModelsCode3
Accelerating the Surrogate Retraining for Poisoning Attacks against Recommender SystemsCode0
Unlearnable Examples Detection via Iterative Filtering—0
Sonic: Fast and Transferable Data Poisoning on Clustering Algorithms—0
2D-OOB: Attributing Data Contribution Through Joint Valuation FrameworkCode0
Show:102550
← PrevPage 2 of 10Next →

No leaderboard results yet.