Privacy

LLM-PBE: Assessing Data Privacy in Large Language Models

A comprehensive privacy assessment of LLMs.

Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk

We propose a new risk to published generative models that finetuning on generated samples can exacerbate the privacy leakage.

DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer

We make local LLMs to engineer privacy-preserving prompts that are transferrable for cloud models.

Understanding Deep Gradient Leakage via Inversion Influence Functions

We propose a new metric to efficiently evaluate the privacy risks from gradient inversion and provides new insights.

A Privacy-Preserving Hybrid Federated Learning Framework for Financial Crime Detection

We develop a hybrid federated learning for learning financial-crime predictive models from horizontal and vertical federated data structures.

Holistic Trustworthy ML

Instead of isolated properties, we target on a holistic trustworthiness covering every properties in one solution.

Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling

We propose a new privacy-preserving learning framework, outsourcing training to cloud without uploading data, which provides more data without injecting noise into gradient or samples.

Dynamic Privacy Budget Allocation Improves Data Efficiency of Differentially Private Gradient Descent

Protecting privacy in learning while maintaining the model performance has become increasingly critical in many applications that involve sensitive data. Private Gradient Descent (PGD) is a commonly used private learning framework, which noises …

Learning Model-Based Privacy Protection under Budget Constraints

Protecting privacy in gradient-based learning has become increasingly critical as more sensitive information is being used. Many existing solutions seek to protect the sensitive gradients by constraining the overall privacy cost within a constant …