Related papers: Audit-LLM: Multi-Agent Collaboration for Log-based…

Large language models (LLMs) are increasingly deployed in collaborative settings, yet little is known about how they coordinate when treated as black-box agents. We simulate 7500 multi-agent, multi-round discussions in an inductive coding…

Anomaly detection (AD) is essential in areas such as fraud detection, network monitoring, and scientific research. However, the diversity of data modalities and the increasing number of specialized AD libraries pose challenges for…

Software logging is critical for system observability, yet developers face a dual crisis of costly overlogging and risky underlogging. Existing automated logging tools often overlook the fundamental whether-to-log decision and struggle with…

Red teaming assesses how large language models (LLMs) can produce content that violates norms, policies, and rules set during their safety training. However, most existing automated methods in the literature are not representative of the…

Building on their demonstrated ability to perform a variety of tasks, we investigate the application of large language models (LLMs) to enhance in-depth analytical reasoning within the context of intelligence analysis. Intelligence analysts…

Logs are ubiquitous digital footprints, playing an indispensable role in system diagnostics, security analysis, and performance optimization. The extraction of actionable insights from logs is critically dependent on the log parsing…

Ethics review is a foundational mechanism of modern research governance, yet contemporary systems face increasing strain as ethical risks arise as structural consequences of large-scale, interdisciplinary scientific practice. The demand for…

Advanced Persistent Threats (APTs) pose a major cybersecurity challenge due to their stealth and ability to mimic normal system behavior, making detection particularly difficult in highly imbalanced datasets. Traditional anomaly detection…

E-commerce platforms increasingly rely on Large Language Models (LLMs) and Vision Language Models (VLMs) to detect illicit or misleading product content. However, these models remain vulnerable to evasive content, which refers to inputs…

Modern large language models (LLMs) like ChatGPT have shown remarkable performance on general language tasks but still struggle on complex reasoning tasks, which drives the research on cognitive behaviors of LLMs to explore human-like…

AI agents, predominantly powered by large language models (LLMs), are vulnerable to indirect prompt injection, in which malicious instructions embedded in untrusted data can trigger dangerous agent actions. This position paper discusses our…

As large language models (LLMs) evolve into autonomous agents capable of collaborative reasoning and task execution, multi-agent LLM systems have emerged as a powerful paradigm for solving complex problems. However, these systems pose new…

Large language models (LLMs) for code are typically trained to align with natural language instructions to closely follow their intentions and requirements. However, in many practical scenarios, it becomes increasingly challenging for these…

Modeling urban crime is an important yet challenging task that requires understanding the subtle visual, social, and cultural cues embedded in urban environments. Previous work has mainly focused on rule-based agent-based modeling (ABM) and…

TThis paper argues that \textbf{a comprehensive vulnerability analysis is essential for building trustworthy Large Language Model-based Multi-Agent Systems (LLM-MAS)}. These systems, which consist of multiple LLM-powered agents working…

This paper presents a novel approach to evaluating the security of large language models (LLMs) against prompt leakage-the exposure of system-level prompts or proprietary configurations. We define prompt leakage as a critical threat to…

As large language models (LLMs) become integral to multi-agent systems, new privacy risks emerge that extend beyond memorization, direct inference, or single-turn evaluations. In particular, seemingly innocuous responses, when composed…

Large language models can deceive by subtly manipulating truthful information -- omitting key facts, shifting focus, or obscuring meaning -- making such behavior difficult to detect. Existing black-box methods rely on coarse-grained…

System logs are a cornerstone of cybersecurity, supporting proactive breach prevention and post-incident investigations. However, analyzing vast amounts of diverse log data remains significantly challenging, as high costs, lack of in-house…

LLM-based agents have recently attracted significant attention due to their ability to autonomously invoke relevant tools to accomplish complex tasks. However, recent studies have shown that these agents face severe security risks, which…