Related papers: Skill Description Deception Attack against Task Ro…
LLM agents are evolving rapidly, powered by code execution, tools, and the recently introduced agent skills feature. Skills allow users to extend LLM applications with specialized third-party code, knowledge, and instructions. Although this…
In recent years, Large-Language-Model-driven AI agents have exhibited unprecedented intelligence and adaptability. Nowadays, agents are undergoing a new round of evolution. They no longer act as an isolated island like LLMs. Instead, they…
The rapid advancement of Large Language Models has given rise to autonomous LLM-based agents capable of complex reasoning and execution. As these agents transition from isolated operation to collaborative ecosystems, we witness the…
Impressive progress has been made in automated problem-solving by the collaboration of large language model (LLM) based agents. However, these automated capabilities also open avenues for malicious applications. In this paper, we study a…
Decentralized training has become a resource-efficient framework to democratize the training of large language models (LLMs). However, the privacy risks associated with this framework, particularly due to the potential inclusion of…
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…
Reusable skills let LLM agents package task-specific procedures, tool affordances, and execution guidance into modular building blocks. As skill ecosystems grow to tens of thousands of entries, exposing every skill at inference time becomes…
This research critically navigates the intricate landscape of AI deception, concentrating on deceptive behaviours of Large Language Models (LLMs). My objective is to elucidate this issue, examine the discourse surrounding it, and…
As large language models (LLMs) are increasingly deployed as interactive agents, open-ended human-AI interactions can involve deceptive behaviors with serious real-world consequences, yet existing evaluations remain largely…
Recent advances in large language models (LLMs) have catalyzed the rise of autonomous AI agents capable of perceiving, reasoning, and acting in dynamic, open-ended environments. These large-model agents mark a paradigm shift from static…
Recent advancements in Web AI agents have demonstrated remarkable capabilities in addressing complex web navigation tasks. However, emerging research shows that these agents exhibit greater vulnerability compared to standalone Large…
With the rapid development of Large Language Models (LLMs), numerous mature applications of LLMs have emerged in the field of content safety detection. However, we have found that LLMs exhibit blind trust in safety detection agents. The…
Message transmission and message synchronization for multicontroller interdomain routing in software-defined networking (SDN) have long adaptation times and slow convergence speeds, coupled with the shortcomings of traditional interdomain…
In this paper, we propose a novel approach where agents can form swarms to produce high-quality responses effectively. This is accomplished by utilizing agents capable of data inference and ranking, which can be effectively implemented…
Large Language Model (LLM)-based agents are increasingly used as autonomous subordinates that carry out tasks for users. This raises the question of whether they may also engage in deception, similar to how individuals in human…
The embedding of Large Language Models (LLMs) into autonomous agents is a rapidly developing field which enables dynamic, configurable behaviours without the need for extensive domain-specific training. In our previous work, we introduced…
Most discussions about Large Language Model (LLM) safety have focused on single-agent settings but multi-agent LLM systems now create novel adversarial risks because their behavior depends on communication between agents and decentralized…
With the continuous evolution of Large Language Models (LLMs), LLM-based agents have advanced beyond passive chatbots to become autonomous cyber entities capable of performing complex tasks, including web browsing, malicious code and…
Recent advances in Large Language Models (LLMs) have catalyzed the development of multi-agent systems (MAS) for complex reasoning tasks. However, existing MAS typically rely on pre-defined or pre-compiled communication topologies, which…
As multi-agent AI systems grow in complexity, the protocols connecting them constrain their capabilities. Current protocols such as A2A and MCP do not expose model-level properties as first-class primitives, ignoring properties fundamental…