works on

From the 1 of 20 linked papers with an AI index.

activity
20242026
collaborators

20 papers

cs.CR2026

Rethinking MCP Security: A Large-Scale Study of Runtime MCP Servers and Security Scanner Reliability

Pei Chen, Baichao An, Mengying Wu +6

The paper introduces MCPZoo, a large collection of over 64 k Model Context Protocol (MCP) servers, and uses it to evaluate the reliability of existing security scanners for MCP ser…

cs.CR2026

The Emergence of Autonomous Penetration Capabilities in Large Language Model-Powered AI Systems

Jiaqi Luo, Jiarun Dai, Zhile Chen +8

Nowadays, the autonomous execution of cyberattacks capable of causing substantial real-world harm is widely regarded as one of the critical red lines that frontier AI systems must…

cs.CR2026

PRISON: Unmasking the Criminal Potential of Large Language Models

Xinyi Wu, Geng Hong, Pei Chen +3

As large language models (LLMs) advance, concerns about their misconduct in complex social contexts intensify. Existing research overlooked the systematic understanding and assessm…

cs.CR2026

AgentCyberRange: Benchmarking Frontier AI Systems in Realistic Cyber Ranges

Fengyu Liu, Jiarun Dai, Yihe Fan +11

Frontier AI systems are increasingly capable of cybersecurity tasks, including codebase inspection, vulnerability detection, and exploitation. However, evaluating their offensive c…

cs.CR2026

CyberEvolver: Structured Self-Evolution for Cybersecurity Agents On the Fly

Yihe Fan, Changyi Li, Lichen Xu +4

LLM-based agents are increasingly used for cybersecurity tasks, but most existing systems rely on fixed, human-designed scaffolds that struggle to adapt across diverse targets and…

cs.CR2026

AgentGuard: An Attribute-Based Access Control Framework for Tool-Use LLM-Based Agent

Jiaqi Luo, Songyang Peng, Jiarun Dai +6

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…