相关论文: COMPASS: A Framework for Evaluating Organization-S…

Ensuring the safety and reliability of large language models (LLMs) in clinical practice is critical to prevent patient harm. However, LLMs are advancing so rapidly that static benchmarks quickly become obsolete or prone to overfitting,…

This paper presents a comprehensive empirical study on the safety alignment capabilities. We evaluate what matters for safety alignment in LLMs and LRMs to provide essential insights for developing more secure and reliable AI systems. We…

Large Language Models (LLMs) are increasingly used to build autonomous agents that perform complex tasks with external tools, often exposed through APIs in enterprise systems. Direct use of these APIs is difficult due to the complex input…

LLM-powered Multi-Agent Systems (LLM-MAS) unlock new potentials in distributed reasoning, collaboration, and task generalization but also introduce additional risks due to unguaranteed agreement, cascading uncertainty, and adversarial…

Conversational Recommender Systems (CRSs) aim to provide personalized recommendations by capturing user preferences through interactive dialogues. Explainability in CRSs is crucial as it enables users to understand the reasoning behind…

Large language models (LLMs) excel at rapid generation of text and multimodal content, yet they falter on transaction-style planning that demands ACID-like guarantees and real-time disruption recovery. We present Adaptive LLM Agent System…

Existing benchmarks for LLM-based vulnerability detection compress model performance into a single metric, which fails to reflect the distinct priorities of different stakeholders. For example, a CISO may emphasize high recall of critical…

LLM-based agents can execute actions that are syntactically valid, user-sanctioned, and semantically appropriate, yet still violate organizational policy because the facts needed for correct policy judgment are hidden at decision time. We…

Large language model agents now act on codebases, browsers, operating systems, calendars, files, and tool ecosystems, but their evaluations often collapse behavior into final task success. AgentAtlas reframes agent evaluation as a…

The growing integration of Large Language Models (LLMs) into critical societal domains has raised concerns about embedded biases that can perpetuate stereotypes and undermine fairness. Such biases may stem from historical inequalities in…

The rapid proliferation of LLM-based autonomous agents in real operating system environments introduces a new category of safety risk beyond content safety: behavior jailbreak, where an adversary induces an agent to execute dangerous…

The growing awareness of safety concerns in large language models (LLMs) has sparked considerable interest in the evaluation of safety. This study investigates an under-explored issue about the evaluation of LLMs, namely the substantial…

Recent advancements in large language models (LLMs) revolutionize the field of intelligent agents, enabling collaborative multi-agent systems capable of tackling complex problems across various domains. However, the potential of conformity…

Compound AI systems (CASs) that employ LLMs as agents to accomplish knowledge-intensive tasks via interactions with tools and data retrievers have garnered significant interest within database and AI communities. While these systems have…

Mobile application marketplaces are responsible for vetting apps to identify and mitigate security risks. Current vetting processes are labor-intensive, relying on manual analysis by security professionals aided by semi-automated tools. To…

HPC systems expose many configuration parameters that jointly drive competing objectives. Existing tools such as autotuners recommend good configurations but do not identify minimal changes for a near-miss configuration to meet a…

Large language models (LLMs) are demonstrating increasing prowess in cybersecurity applications, creating creating inherent risks alongside their potential for strengthening defenses. In this position paper, we argue that current efforts to…

Large Language Models (LLMs) are increasingly integrated into safety-critical workflows, yet existing security analyses remain fragmented and often isolate model behavior from the broader system context. This work introduces a goal-driven…

The popularity of large language models (LLMs) continues to grow, and LLM-based assistants have become ubiquitous. Information security awareness (ISA) is an important yet underexplored area of LLM safety. ISA encompasses LLMs' security…

As AI agents built on large language models (LLMs) become increasingly embedded in society, issues of coordination, control, delegation, and accountability are entangled with concerns over their reliability. To design and implement LLM…