相关论文: SOCpilot: Verifying Policy Compliance for LLM-Assi…

Large language models (LLMs) are increasingly used to generate requirements specifications, design documents, code, and test cases. In contrast, much less attention has been given to a more difficult assurance problem: statically verifying…

Ensuring the reliability and availability of complex networked services demands effective root cause analysis (RCA) across cloud environments, data centers, and on-premises networks. Traditional RCA methods, which involve manual inspection…

Large Language Models (LLMs) are increasingly being used as autonomous agents capable of performing complicated tasks. However, they lack the ability to perform reliable long-horizon planning on their own. This paper bridges this gap by…

Security operation centers contend with a constant stream of security incidents, ranging from straightforward to highly complex. To address this, we developed Microsoft Copilot for Security Guided Response (CGR), an industry-scale ML…

Ensuring the security of complex system-on-chips (SoCs) designs is a critical imperative, yet traditional verification techniques struggle to keep pace due to significant challenges in automation, scalability, comprehensiveness, and…

In modern energy systems, industrial control systems (ICS) and power-system SCADA require intrusion detection that is not only accurate but also auditable by operators. The ICS intrusion-detection landscape is currently dominated by…

Robotics researchers increasingly leverage large language models (LLM) in robotics systems, using them as interfaces to receive task commands, generate task plans, form team coalitions, and allocate tasks among multi-robot and human agents.…

While explicit Chain-of-Thought (CoT) empowers large reasoning models (LRMs), it enables the generation of riskier final answers. Current alignment paradigms primarily rely on externally enforced compliance, optimizing models to detect…

We introduce the Cyber Defense Benchmark, a benchmark for measuring how well large language model (LLM) agents perform the core SOC analyst task of threat hunting: given a database of raw Windows event logs with no guided questions or…

As large language models (LLMs) evolve from conversational assistants into autonomous agents, evaluating the safety of their actions becomes critical. Prior safety benchmarks have primarily focused on preventing generation of harmful…

Hardware security verification is a challenging and time-consuming task. Design engineers may use formal verification, linting, and functional simulation tests, coupled with analysis and a deep understanding of the hardware design being…

Credible safety plans for advanced AI development require methods to verify agent behavior and detect potential control deficiencies early. A fundamental aspect is ensuring agents adhere to safety-critical principles, especially when these…

We study how runtime enforcement against unsafe actions affects end-to-end task performance in multi-step tool using large language model (LLM) agents. Using tau-bench across Airline and Retail domains, we compare baseline Tool-Calling,…

Large Language Model (LLM)-based agents are increasingly employed to automate complex software engineering tasks, such as program repair and issue resolution. These agents operate by autonomously generating natural language thoughts,…

Large Language Models (LLMs) are increasingly used as core dependencies in software systems. However, the hosted LLM services evolve continuously through provider-side updates without explicit version changes. These silent updates can…

We present a framework in which a large language model (LLM) acts as an online adaptive controller for SIMP topology optimization, replacing conventional fixed-schedule continuation with real-time, state-conditioned parameter decisions. At…

Large Language Model (LLM) agents increasingly act through external tools, making their safety contingent on tool-call workflows rather than text generation alone. While recent benchmarks evaluate agents across diverse environments and risk…

Large language models (LLMs) have demonstrated remarkable capabilities in tool learning. In real-world scenarios, user queries are often ambiguous and incomplete, requiring effective clarification. However, existing interactive…

Financial institutions deploy Large Language Models (LLMs) for reconciliations, regulatory reporting, and client communications, but nondeterministic outputs (output drift) undermine auditability and trust. We quantify drift across five…

Recent high profile incidents in which the use of Large Language Models (LLMs) resulted in significant harm to individuals have brought about a growing interest in AI safety. One reason LLM safety issues occur is that models often have at…