相关论文: A Logic of Sattestation

Trusted Execution Environments (TEEs) are a feature of modern central processing units (CPUs) that aim to provide a high assurance, isolated environment in which to run workloads that demand both confidentiality and integrity. Hardware and…

Experience shows that most researchers and developers tend to treat plain-domains (those that are not prefixed with "www" sub-domains, e.g. "example.com") as synonyms for their equivalent www-domains (those that are prefixed with "www"…

\textbf{Background:} Regulatory frameworks for AI in healthcare, including the EU AI Act and FDA guidance on AI/ML-based medical devices, require clinical decision support to demonstrate not only accuracy but auditability. Existing formal…

Automated verification of security protocols based on dynamic root of trust, typically relying on protected hardware such as TPM, involves several challenges that we address in this paper. We model the semantics of trusted computing…

Trust prediction provides valuable support for decision-making, risk mitigation, and system security enhancement. Recently, Graph Neural Networks (GNNs) have emerged as a promising approach for trust prediction, owing to their ability to…

Current advances in AI and its applicability have highlighted the need to ensure its trustworthiness for legal, ethical, and even commercial reasons. Sub-symbolic machine learning algorithms, such as the LLMs, simulate reasoning but…

With the rise of network science old topics in ecology and economics are resurfacing. One such topic is structural stability (often referred to as qualitative stability or sign stability). A system is deemed structurally stable if the…

Large Language Models (LLMs) are often augmented with external contexts, such as those used in retrieval-augmented generation (RAG). However, these contexts can be inaccurate or intentionally misleading, leading to conflicts with the…

Belief systems are rarely globally consistent, yet effective reasoning often persists locally. We propose a novel graph-theoretic framework that cleanly separates credibility--external, a priori trust in sources--from confidence--an…

As AI systems increasingly influence critical decisions, they face threats that exploit reasoning mechanisms rather than technical infrastructure. We present a framework for cognitive cybersecurity, a systematic protection of AI reasoning…

Root of Trust Identification (RTI) refers to determining whether a given security service or task is being performed by the particular root of trust (e.g., a TEE) within a specific physical device. Despite its importance, this problem has…

The use of connected surgical robotics to automate medical procedures presents new privacy challenges. We argue that conventional patient consent protocols no longer work. Indeed robots that replace human surgeons take on an extraordinary…

Reputation systems guide our decision making both in life and work: which restaurant to eat at, which vendor to buy from, which software dependencies to use, and who or what to trust. These systems are often based on old ideas and are…

Trust is a fundamental concept in human decision-making and collaboration that has long been studied in philosophy and psychology. However, software engineering (SE) articles often use the term trust informally; providing an explicit…

The Internet Domain Name System (DNS) is a hierarchical name space that enables the assignment of unique, mnemonic identifiers to Internet hosts and the consistent mapping of these names to IP addresses. The root of the domain name system…

The DNS HTTPS resource record is a new DNS record type designed for the delivery of configuration information and parameters required to initiate connections to HTTPS network services. In addition, it is a key enabler for TLS Encrypted…

Large language models (LLMs) have made significant advancements across various tasks, but their safety alignment remain a major concern. Exploring jailbreak prompts can expose LLMs' vulnerabilities and guide efforts to secure them. Existing…

The Internet's TCP/IP architecture was designed for resilient packet delivery between hosts identified by IP addresses. Over time, however, the consolidation of applications and services into large-scale platforms built on that universal…

In a variety of applications, there is a need to authenticate content that has experienced legitimate editing in addition to potential tampering attacks. We develop one formulation of this problem based on a strict notion of security, and…

Controllers for structured LM reasoning (e.g., Chain-of-Thought, self-consistency, and Tree-of-Thoughts) often entangle what to try next with how to execute it, exposing only coarse global knobs and yielding brittle, compute-inefficient,…