# data
13 articlestagged with “data”
Function Calling Data Exfiltration
Using function calls as data exfiltration channels to extract information from constrained environments.
Data Privacy in AI Assessment
Assessment on training data privacy, membership inference, data extraction, and privacy-preserving techniques.
Gradient Leakage Attacks
Extracting training data from gradient updates in federated and collaborative learning settings.
Training Data Memorization Exploitation
Techniques for exploiting model memorization to extract verbatim training examples.
Property Inference Attacks
Inferring global properties of training datasets through model behavior analysis.
Practical Synthetic Data Poisoning
Poisoning synthetic data generation pipelines used for model training augmentation.
Data Heist Challenge
Extract a secret database of customer records from a RAG-enabled chatbot with strict data access controls.
Feature Store Security
Securing feature stores used in ML pipelines against poisoning and unauthorized access.
Pre-Training Data Attacks
Attacking the pre-training data pipeline including web crawl poisoning and data curation manipulation.
Preference Data Poisoning (Training Pipeline)
Poisoning preference data used in RLHF and DPO to shift model alignment toward attacker objectives.
Training Data Provenance Attacks
Attacking training data provenance and attribution systems to inject unverified data sources.
Data Harvesting Through LLM Apps
Complete walkthrough of systematic data extraction from LLM applications using various exfiltration channels.
RAG Poisoning End-to-End Walkthrough
Complete walkthrough of poisoning a RAG system from document injection through information extraction.