相关论文: Declarative Reconfigurable Trust Management

We present SAFE, an integrated system for managing trust using a logic-based declarative language. Logical trust systems authorize each request by constructing a proof from a context---a set of authenticated logic statements representing…

We present SBTrust, a logical framework designed to formalize decision trust. Our logic integrates a doxastic modality with a novel non-monotonic conditional operator that establishes a positive support relation between statements, and is…

Recent developments in Distributed Ledger Technology (DLT), including Blockchain offer new opportunities in the manufacturing domain, by providing mechanisms to automate trust services (digital identity, trusted interactions, and auditable…

Large Language Models generate complex reasoning chains that reveal their decision-making, yet verifying the faithfulness and harmlessness of these intermediate steps remains a critical unsolved problem. Existing auditing methods are…

Blockchains are being positioned as the "technology of trust" that can be used to mediate transactions between non-trusting parties without the need for a central authority. They support transaction types that are native to the blockchain…

Despite substantial advancements in aligning large language models (LLMs) with human values, current safety mechanisms remain susceptible to jailbreak attacks. We hypothesize that this vulnerability stems from distributional discrepancies…

Large Language Models (LLMs) are increasingly used for planning tasks, offering unique capabilities not found in classical planners such as generating explanations and iterative refinement. However, trust--a critical factor in the adoption…

High-stakes decision domains are increasingly exploring the potential of Large Language Models (LLMs) for complex decision-making tasks. However, LLM deployment in real-world settings presents challenges in data security, evaluation of its…

Large Language Models (LLMs) have transformed natural language processing (NLP) by enabling robust text generation and understanding. However, their deployment in sensitive domains like healthcare, finance, and legal services raises…

LLM-powered coding and development assistants have become prevalent to programmers' workflows. However, concerns about the trustworthiness of LLMs for code persist despite their widespread use. Much of the existing research focused on…

Despite the superior capabilities of Multimodal Large Language Models (MLLMs) across diverse tasks, they still face significant trustworthiness challenges. Yet, current literature on the assessment of trustworthy MLLMs remains limited,…

The growing number of individual generating units, hybrid resources, and security constraints has significantly increased the computational burden of network-constrained unit commitment (UC), where most solution time is spent exploring…

Trustworthiness and interpretability are inextricably linked concepts for LLMs. The more interpretable an LLM is, the more trustworthy it becomes. However, current techniques for interpreting LLMs when applied to code-related tasks largely…

Financial institutions of all sizes are increasingly adopting Large Language Models (LLMs) to enhance credit assessments, deliver personalized client advisory services, and automate various language-intensive processes. However, effectively…

The deployment of Large Reasoning Models (LRMs) in high-stakes decision-making pipelines has introduced a novel and opaque attack surface: reasoning backdoors. In these attacks, the model's intermediate Chain-of-Thought (CoT) is manipulated…

Multimodal large language models (MLLMs) hold considerable promise for applications in healthcare. However, their deployment in safety-critical settings is hindered by two key limitations: (i) sensitivity to prompt design, and (ii) a…

Large Language Models (LLMs) are increasingly deployed in sensitive domains such as healthcare, finance, and law, yet their integration raises pressing concerns around trust, accountability, and reliability. This paper explores adaptive…

Increasing complexity in software systems places a growing demand on reasoning tools that unlock vulnerabilities manifest in source code. Many current approaches focus on vulnerability analysis as a classifying task, oversimplifying the…

The pre-training paradigm plays a key role in the success of Large Language Models (LLMs), which have been recognized as one of the most significant advancements of AI recently. Building on these breakthroughs, code LLMs with advanced…

We present CLTLB(D), an extension of PLTLB (PLTL with both past and future operators) augmented with atomic formulae built over a constraint system D. Even for decidable constraint systems, satisfiability and Model Checking problem of such…