PCEvolve: Private Contrastive Evolution for Synthetic Dataset Generation Via Few-Shot Private Data and Generative APIs

The rise of generative APIs has fueled interest in privacy-preserving synthetic data generation. While the Private Evolution PE algorithm generates Differential Privacy DP synthetic images using diffusion model APIs, it struggles with few-shot private data due to the limitations of its DP-protect...

Clustering and Median Aggregation Improve Differentially Private Inference

Differentially private DP language model inference is an approach for generating private synthetic text. A sensitive input example is used to prompt an off-the-shelf large language model LLM to produce a similar example. Multiple examples can be aggregated together to formally satisfy the DP...

SMOTE-DP: Improving Privacy-Utility Tradeoff with Synthetic Data

Privacy-preserving data publication, including synthetic data sharing, often experiences trade-offs between privacy and utility. Synthetic data is generally more effective than data anonymization in balancing this trade-off, however, not without its own challenges. Synthetic data produced by...

Dpmm: Differentially Private Marginal Models, a Library for Synthetic Tabular Data Generation

We propose dpmm, an open-source library for synthetic data generation with Differentially Private DP guarantees. It includes three popular marginal models -- PrivBayes, MST, and AIM -- that achieve superior utility and offer richer functionality compared to alternative implementations...

USB: a Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models

Despite their remarkable achievements and widespread adoption, Multimodal Large Language Models MLLMs have revealed significant security vulnerabilities, highlighting the urgent need for robust safety evaluation benchmarks. Existing MLLM safety benchmarks, however, fall short in terms of data...

Toward Malicious Clients Detection in Federated Learning

Federated learning FL enables multiple clients to collaboratively train a global machine learning model without sharing their raw data. However, the decentralized nature of FL introduces vulnerabilities, particularly to poisoning attacks, where malicious clients manipulate their local models to...

Privacy-Preserving Analytics for Smart Meter (AMI) Data: a Hybrid Approach to Comply with CPUC Privacy Regulations

Advanced Metering Infrastructure AMI data from smart electric and gas meters enables valuable insights for utilities and consumers, but also raises significant privacy concerns. In California, regulatory decisions CPUC D.11-07-056 and D.11-08-045 mandate strict privacy protections for customer...

The DCR Delusion: Measuring the Privacy Risk of Synthetic Data

Synthetic data has become an increasingly popular way to share data without revealing sensitive information. Though Membership Inference Attacks MIAs are widely considered the gold standard for empirically assessing the privacy of a synthetic dataset, practitioners and researchers often rely on...

Enhancing Leakage Attacks on Searchable Symmetric Encryption Using LLM-Based Synthetic Data Generation

Searchable Symmetric Encryption SSE enables efficient search capabilities over encrypted data, allowing users to maintain privacy while utilizing cloud storage. However, SSE schemes are vulnerable to leakage attacks that exploit access patterns, search frequency, and volume information. Existing...

Optimizing the Privacy-Utility Balance Using Synthetic Data and Configurable Perturbation Pipelines

This paper explores the strategic use of modern synthetic data generation and advanced data perturbation techniques to enhance security, maintain analytical utility, and improve operational efficiency when managing large datasets, with a particular focus on the Banking, Financial Services, and...

Private Federated Learning Using Preference-Optimized Synthetic Data

In practical settings, differentially private Federated learning DP-FL is the dominant method for training models from private, on-device client data. Recent work has suggested that DP-FL may be enhanced or outperformed by methods that use DP synthetic data Wu et al., 2024; Hou et al., 2024. The...

Leveraging Vertical Public-Private Split for Improved Synthetic Data Generation

Differentially Private Synthetic Data Generation DP-SDG is a key enabler of private and secure tabular-data sharing, producing artificial data that carries through the underlying statistical properties of the input data. This typically involves adding carefully calibrated statistical noise to...

The AI Dividend

For four decades, Alaskans have opened their mailboxes to find checks waiting for them, their cut of the black gold beneath their feet. This is Alaskas Permanent Fund, funded by the states oil revenues and paid to every Alaskan each year. Were now in a different sort of resource rush, with...

P = NP: Cloud data protection in vulnerable non-production environments

Data is the holy grail of your cloud workloads for attackers. Data breaches are the kind of breaches that make the news. With the recent European Union General Data Protection Regulations GDPR, they will make even bigger headlines. From an enterprise point of view, the most challenging aspect of...