Related papers: TrinityGuard: A Unified Framework for Safeguarding…
Real-world visualization tasks involve complex, multi-modal requirements that extend beyond simple text-to-chart generation, requiring reference images, code examples, and iterative refinement. Current systems exhibit fundamental…
Multi-agent systems (MAS) decompose complex tasks and delegate subtasks to different large language model (LLM) agents and tools. Prior studies have reported the superior accuracy performance of MAS across diverse domains, enabled by…
Large language models enable agents to autonomously perform tasks in open web environments. However, as hidden threats within the web evolve, web agents face the challenge of balancing task performance with emerging risks during…
Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding, code generation, and complex planning. Simultaneously, Multi-Agent Systems (MAS) have garnered attention for their potential to enable…
Autonomous agents based on large language models (LLMs) are rapidly emerging as a general-purpose technology, with recent systems such as OpenClaw extending their capabilities through broad tool use, third-party skills, and deeper…
The rapid evolution of sophisticated cyberattacks has strained modern Security Operations Centers (SOC), which traditionally rely on rule-based or signature-driven detection systems. These legacy frameworks often generate high volumes of…
LLM-based Multi-Agent Systems ( LLM-MAS ) have become a research hotspot since the rise of large language models (LLMs). However, with the continuous influx of new related works, the existing reviews struggle to capture them…
This position paper argues that enforcing LLM agent safety within a single abstraction layer is not merely suboptimal but categorically insufficient for deployed LLM agents -- a structural consequence of how agent execution works, not a…
LLM-based agents are becoming increasingly capable, yet their safety lags behind. This creates a gap between what agents can do and should do. This gap widens as agents engage in multi-turn interactions and employ diverse tools, introducing…
Multimodal large language models (MLLMs) have shown remarkable capabilities in cross-modal understanding and reasoning, offering new opportunities for intelligent assistive systems, yet existing systems still struggle with risk-aware…
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…
The integration of Large Language Models (LLMs) and Multi-modal Large Language Models (MLLMs) into mobile GUI agents has significantly enhanced user efficiency and experience. However, this advancement also introduces potential security…
Multi-agent systems (MAS) powered by LLMs promise adaptive, reasoning-driven enterprise workflows, yet granting agents autonomous control over tools, memory, and communication introduces attack surfaces absent from deterministic pipelines.…
Although LLM-based agents, powered by Large Language Models (LLMs), can use external tools and memory mechanisms to solve complex real-world tasks, they may also introduce critical security vulnerabilities. However, the existing literature…
Recent advances in multi-modal large language models (MLLMs) have enabled unified perception-reasoning capabilities, yet these systems remain highly vulnerable to jailbreak attacks that bypass safety alignment and induce harmful behaviors.…
Large Language Model based multi-agent systems are revolutionizing autonomous communication and collaboration, yet they remain vulnerable to security threats like unauthorized access and data breaches. To address this, we introduce…
In the rapidly evolving landscape of Large Language Models (LLMs), ensuring robust safety measures is paramount. To meet this crucial need, we propose \emph{SALAD-Bench}, a safety benchmark specifically designed for evaluating LLMs, attack,…
Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks. However, this communication also creates an attack surface where malicious…
Multi-agent systems (MAS) have emerged as a prominent paradigm for leveraging large language models (LLMs) to tackle complex tasks. However, the mechanisms governing the effectiveness of MAS built upon publicly available LLMs, specifically…
The emergence of Large Language Models (LLMs) is rapidly accelerating the development of autonomous multi-agent systems (MAS), paving the way for the Internet of Agents. However, traditional centralized MAS architectures present significant…