Related papers: Beyond Single-Agent Alignment: Preventing Context-…

Modern Security Operations Centers struggle with alert fatigue, fragmented tooling, and limited cross-source event correlation. Challenges that current Security Information Event Management and Extended Detection and Response systems only…

Multi-agent applications have recently gained significant popularity. In many computer vision tasks, a network of agents, such as a team of robots with cameras, could work collaboratively to perceive the environment for efficient and…

Current research on large language model (LLM) agents is fragmented: discussions of conceptual frameworks and methodological principles are frequently intertwined with low-level implementation details, causing both readers and authors to…

Multi-agent systems powered by large language models are advancing rapidly, yet the tension between mutual trust and security remains underexplored. We introduce and empirically validate the Trust-Vulnerability Paradox (TVP): increasing…

In this paper, a class of convex feasibility problems (CFPs) are studied for multi-agent systems through local interactions. The objective is to search a feasible solution to the convex inequalities with some set constraints in a…

An attacker can split a malicious goal into sub-prompts that each look benign on their own and only become harmful in combination. Existing LLM safety benchmarks evaluate prompts one at a time, or across turns of a single chat, and so do…

Large Language Models (LLMs) are increasingly deployed as autonomous agents, yet their practical utility is fundamentally constrained by a limited context window and state desynchronization resulting from the LLMs' stateless nature and…

Ensuring safety in multi-agent systems is a significant challenge, particularly in settings where centralized coordination is impractical. In this work, we propose a novel risk-sensitive safety filter for discrete-time multi-agent systems…

Multi-stage threats like advanced persistent threats (APT) pose severe risks by stealing data and destroying infrastructure, with detection being challenging. APTs use novel attack vectors and evade signature-based detection by obfuscating…

The integration of vision-language models (VLMs) is driving a new generation of embodied agents capable of operating in human-centered environments. However, as deployment expands, these systems face growing safety risks, particularly when…

As Large Language Model (LLM) based Multi-Agent Systems (MAS) evolve from experimental pilots to complex, persistent ecosystems, the limitations of direct agent-to-agent communication have become increasingly apparent. Current architectures…

One salient feature of cooperative formation tracking is its distributed nature that relies on localized control and information sharing over a sparse communication network. That is, a distributed control manner could be prone to malicious…

Decentralized strategies are of interest for local decision-making over multi-vehicle networks. This paper studies mixed traffic networks of human-driven and autonomous vehicles with partial sensor measurements. The idea is to enable the…

As agentic network management gains popularity, there is a critical need for evaluation frameworks that transcend static, one-shot testing. To address this, we introduce NetAgentBench, a dynamic benchmark that evaluates agent interactions…

Large language models (LLMs) often require fine-tuning (FT) to perform well on downstream tasks, but FT can induce safety-alignment drift even when the training dataset contains only benign data. Prior work shows that introducing a small…

Existing benchmarks for LLM-based offensive security agents use isolated, single-target setups with a known vulnerable service and fixed objective. They measure exploitation effectively, but miss how real Capture-the-Flag (CTF) participants…

Multi-agent LLM systems have shown promise for complex reasoning, yet recent evaluations reveal they often underperform single-model baselines. We identify a structural failure mode in sequential fine-tuning of shared-context teams:…

Large language model (LLM) agents are increasingly deployed in personalized tasks involving sensitive, context-dependent information, where privacy violations may arise in agents' action due to the implicitness of contextual privacy.…

Modern LLM based agents are no longer passive text generators. They read repositories, call tools, browse the web, execute code, maintain memory, communicate with other agents, and act through long horizon workflows. This shift moves the…

Despite the growing capabilities of autonomous agents powered by large language models (LLMs), their adoption in high-stakes domains remains limited. A key barrier is security: the inherently nondeterministic behavior of LLM agents defies…