相关论文: The VACCINE Framework for Building DLP Systems

The exponential growth of data collection necessitates robust privacy protections that preserve data utility. We address information disclosure against adversaries with bounded prior knowledge, modeled by an entropy constraint $H(X) \geq…

Designing effective strategies for controlling epidemic spread by vaccination is an important question in epidemiology, especially in the early stages when vaccines are limited. This is a challenging question when the contact network is…

Automating software vulnerability detection (SVD) remains a critical challenge in an era of increasingly complex and interdependent software systems. Despite significant advances in Large Language Models (LLMs) for code analysis, prevailing…

Deep neural networks (DNNs) have demonstrated their superiority in practice. Arguably, the rapid development of DNNs is largely benefited from high-quality (open-sourced) datasets, based on which researchers and developers can easily…

The growing use of large language models in sensitive domains has exposed a critical weakness: the inability to ensure that private information can be permanently forgotten. Yet these systems still lack reliable mechanisms to guarantee that…

Differential Privacy (DP) has emerged as a robust framework for privacy-preserving data releases and has been successfully applied in high-profile cases, such as the 2020 US Census. However, in organizational settings, the use of DP remains…

The increasing popularity of machine learning approaches and the rising awareness of data protection and data privacy presents an opportunity to build truly secure and trustworthy healthcare systems. Regulations such as GDPR and HIPAA…

Recent advancements in Large Language Models (LLMs) have significantly improved text generation capabilities. However, they also present challenges, particularly in generating vaccine-related misinformation, which poses risks to public…

Privacy preserving machine learning deployments in sensitive deep learning applications; from medical imaging to autonomous systems; increasingly require combining multiple techniques. Yet, practitioners lack systematic guidance to assess…

Verifiable ledger databases protect data history against malicious tampering. Existing systems, such as blockchains and certificate transparency, are based on transparency logs -- a simple abstraction allowing users to verify that a log…

Empirical natural language processing (NLP) systems in application domains (e.g., healthcare, finance, education) involve interoperation among multiple components, ranging from data ingestion, human annotation, to text retrieval, analysis,…

The integration of AI components, particularly Deep Neural Networks (DNNs), into safety-critical systems such as aerospace and autonomous vehicles presents fundamental challenges for assurance. The opacity of AI systems, combined with the…

Synthetic text generation with Differential Privacy (DP) guarantees emerges as a principled approach that can enable the sharing of sensitive datasets across institutional and regulatory boundaries, while bounding the risks of…

Epidemic analyses increasingly rely on heterogeneous datasets, many of which are sensitive and require strong privacy protection. Although differential privacy (DP) has become a standard in machine learning and data sharing, its adoption in…

Text rewriting with differential privacy (DP) provides concrete theoretical guarantees for protecting the privacy of individuals in textual documents. In practice, existing systems may lack the means to validate their privacy-preserving…

The rapid development of language models (LMs) brings unprecedented accessibility and usage for both models and users. On the one hand, powerful LMs achieve state-of-the-art performance over numerous downstream NLP tasks. On the other hand,…

The security guarantee of AI-enabled software systems (particularly using deep learning techniques as a functional core) is pivotal against the adversarial attacks exploiting software vulnerabilities. However, little attention has been paid…

The rapid advancement of Large Language Models (LLMs) has driven significant progress in Natural Language Interface to Database (NLIDB). However, the widespread adoption of LLMs has raised critical privacy and security concerns. During…

In this paper, we propose a tool, called DataProVe, for specifying high-level data protection policies and system architectures, as well as verifying the conformance between them in a fully automated way. The syntax of the policies and the…

Privacy research has attracted wide attention as individuals worry that their private data can be easily leaked during interactions with smart devices, social platforms, and AI applications. Computer science researchers, on the other hand,…