相关论文: The VACCINE Framework for Building DLP Systems

In-context learning (ICL) in Large Language Models (LLMs) has shown remarkable performance across various tasks without requiring fine-tuning. However, recent studies have highlighted the risk of private data leakage through the prompt in…

A Data Ecosystem offers a keystone-player or alliance-driven infrastructure that enables the interaction of different stakeholders and the resolution of interoperability issues among shared data. However, despite years of research in data…

In current inter-organizational data spaces, usage policies are enforced mainly at the asset level: a whole document or dataset is either shared or withheld. When only parts of a document are sensitive, providers who want to avoid leaking…

Website privacy policies are too long to read and difficult to understand. The over-sophisticated language makes privacy notices to be less effective than they should be. People become even less willing to share their personal information…

We study privacy guarantees in the framework of pointwise maximal leakage (PML) that satisfy two requirements: they are robust under post-processing and upper bound the failure probability, i.e., the probability that the information leakage…

Understanding and extracting structured insights from unstructured documents remains a foundational challenge in industrial NLP. While Large Language Models (LLMs) enable zero-shot extraction, traditional pipelines often fail to handle…

As Model Context Protocol (MCP) introduces an easy-to-use ecosystem for users and developers, it also brings underexplored safety risks. Its decentralized architecture, which separates clients and servers, poses unique challenges for…

The development of Large Language Models (LLMs) has led to significant advancements in natural language processing and enabled numerous applications across various industries. However, many LLM-based solutions operate as open systems…

Pipeline parallelism is an essential distributed parallelism method. Increasingly complex and diverse DNN models necessitate meticulously customized pipeline schedules for performance. However, existing practices typically rely on…

This position paper argues that securing LLM agents requires first defining an end-to-end correctness property that specifies when an agent's execution faithfully reflects the user's intent. Modern LLM agents operate over an…

Despite the rise of data-driven software systems in the modern digital landscape, data governance under a legal framework remains a critical challenge. In India, the Digital Personal Data Protection (DPDP) Act mandates rigorous data privacy…

Modern Integrated Development Environments (IDEs) increasingly leverage Large Language Models (LLMs) to provide advanced features like code autocomplete. While powerful, training these models on user-written code introduces significant…

The complexity of modern integrated circuits (ICs) necessitates collaboration between multiple distrusting parties, including thirdparty intellectual property (3PIP) vendors, design houses, CAD/EDA tool vendors, and foundries, which…

Healthcare AI systems face major vulnerabilities to data poisoning that current defenses and regulations cannot adequately address. We analyzed eight attack scenarios in four categories: architectural attacks on convolutional neural…

The problem of data contamination is now almost inevitable during the development of large language models (LLMs), with the training data commonly integrating those evaluation benchmarks even unintentionally. This problem subsequently makes…

LLM-based coding agents extend their capabilities via third-party agent skills distributed through open marketplaces without mandatory security review. Unlike traditional packages, these skills are executed as operational directives with…

Blockchain is an incipient technology that offers many strengths compared to traditional systems, such as decentralization, transparency and traceability. However, if the technology is to be used for processing personal data, complementary…

Vision-and-Language Navigation (VLN) requires an embodied agent to navigate in a complex 3D environment according to natural language instructions. Recent progress in large language models (LLMs) has enabled language-driven navigation with…

The increasing autonomy of LLM agents in handling sensitive communications, accelerated by Model Context Protocol (MCP) and Agent-to-Agent (A2A) frameworks, creates urgent privacy challenges. While recent work reveals significant gaps…

Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled powerful autonomous agents capable of complex reasoning and multi-modal tool use. Despite their growing capabilities, today's agent frameworks…