Related papers: AEX: Non-Intrusive Multi-Hop Attestation and Prove…

Public agencies are beginning to consider large language models (LLMs) as decision-support tools for grant evaluation. This creates a practical governance problem: the model and scoring rubric should not be exposed in a way that allows…

Recent advances in large language models (LLMs) have enabled a new generation of autonomous agents that operate over sustained periods and manage sensitive resources on behalf of users. Trusted for their ability to act without direct…

HEX-programs are an extension of answer set programs (ASP) with external sources. To this end, external atoms provide a bidirectional interface between the program and an external source. The traditional evaluation algorithm for…

Enterprise AI backends increasingly admit heterogeneous execution requests across model deployment, inference, evaluation, data movement, and agentic workflows. In many systems, those requests arrive in service-specific shapes, which makes…

Process attestation systems verify that a continuous physical process, such as human authorship, actually occurred, rather than merely checking system state. These systems face a fundamental dependability challenge: the evidence collection…

Hypertext Transfer Protocol Secure (HTTPS) protocol has become an integral part of modern Internet technology. Currently, it is the primary protocol for commercialized web applications. It can provide a fast, secure connection with a…

REST APIs are prevalent among web service implementations, easing interoperability through the HTTP protocol. API testers and users exploit the widely adopted OpenAPI Specification (OAS), a machine-readable standard to document REST APIs.…

The Model Context Protocol (MCP) standardizes how a large-language-model (LLM) agent and an external tool server exchange messages, but not trust: a host reads a server's self-declared tool list and dispatches calls, with no notion of which…

Intel(R) Software Guard Extensions (Intel(R) SGX) is a promising technology to securely process information in otherwise untrusted environments. An important aspect of Intel SGX is the ability to perform remote attestation to assess the…

Large language models are increasingly deployed in streaming scenarios, rendering conventional post-hoc safeguards ineffective as they fail to interdict unsafe content in real-time. While streaming safeguards based on token-level supervised…

Confidential computing is a security paradigm that enables the protection of confidential code and data in a co-tenanted cloud deployment using specialized hardware isolation units called Trusted Execution Environments (TEEs). By…

Hardware-secured remote attestation is essential to establishing trust in the integrity of confidential virtual machines (cVMs), but is difficult to use in practice because verifying attestation evidence requires the use of…

Data theft and leakage, caused by external adversaries and insiders, demonstrate the need for protecting user data. Trusted Execution Environments (TEEs) offer a promising solution by creating secure environments that protect data and code…

Benchmarks are important measures to evaluate safety and compliance of AI models at scale. However, they typically do not offer verifiable results and lack confidentiality for model IP and benchmark datasets. We propose Attestable Audits,…

Modern Large Language Model (LLM) systems are assembled from third-party artifacts such as pre-trained weights, fine-tuning adapters, datasets, dependency packages, and container images, fetched through automated pipelines. This speed comes…

Explainable AI (XAI) has achieved remarkable success in image classification, yet the audio domain lacks equally mature solutions. Current methods apply vision-based attribution techniques to spectrograms, overlooking fundamental…

Commercial Large Language Model (LLM) APIs create a fundamental trust problem: users pay for specific models but have no guarantee that providers deliver them faithfully. Providers may covertly substitute cheaper alternatives (e.g.,…

Trusted Execution Environments (TEEs) are designed to protect the privacy and integrity of data in use. They enable secure data processing and sharing in peer-to-peer networks, such as vehicular ad hoc networks of autonomous vehicles,…

Embedded devices are increasingly ubiquitous and their importance is hard to overestimate. While they often support safety-critical functions (e.g., in medical devices and sensor-alarm combinations), they are usually implemented under…

Large scale deep learning model, such as modern language models and diffusion architectures, have revolutionized applications ranging from natural language processing to computer vision. However, their deployment in distributed or…