arXiv subjects

Xudong Pan

Publications and source records attributed to Xudong Pan.

At least 19 recordsLinked to original sources

arXiv2026

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

The Model Context Protocol (MCP) has rapidly established itself as a standard interface for enabling LLM-based agents to interact with external tools and services. As MCP servers are increasingly entrusted with security-sensitive operations, understanding their real-world risks has become critical. In practice, due to the absence of large-scale runtime MCP servers, such understanding largely relies on security scanners applied to a small number of cases, yet the reliability of these assessments remains unclear. In this study, we revisit how MCP security is measured. We present MCPZoo, the largest collection of MCP servers for dynamic analysis to date. MCPZoo is constructed through a multi-agent framework for transforming in-the-wild static repositories into dynamic services. The framework emulates how human experts build, diagnose, and iteratively repair deployment and runtime defects by combining environment inference with feedback-driven refinement. To ensure practical interactivity at runtime, the servers are validated via real protocol interactions. As a result, MCPZoo contains 64,611 unique MCP servers (113,927 in total), with more than 37,288 supporting dynamic analysis. Leveraging MCPZoo, we conduct the first ecosystem-scale measurement of MCP servers and the scanners that analyze them. While existing scanners report that 96.89% of servers are risky, we find that these signals are unreliable. In particular, manual validation shows that less than 50% of sampled alerts are true positives, and scanner outputs exhibit clear inconsistency across scanners. Overall, MCPZoo enables large-scale, reproducible measurement of MCP server security and exposes limitations of current scanning practices. We further release a public query interface to support practical risk assessment of MCP servers.

cs.CR↗

arXiv2026

AgentCyberRange: Benchmarking Frontier AI Systems in Realistic Cyber Ranges

Frontier AI systems are increasingly capable of cybersecurity tasks, including codebase inspection, vulnerability detection, and exploitation. However, evaluating their offensive capabilities remains constrained by limited access to open, reproducible, multi-host cyber ranges. Existing public benchmarks capture isolated skills such as CTF solving, vulnerability reproduction, and exploit generation, but often abstract away realistic intrusion workflows: discovering exposed services, gaining a foothold, collecting internal information, and expanding compromise across hosts. This gap makes it difficult to observe emerging risks early, because frontier AI systems are rarely evaluated under realistic attack conditions. We introduce AgentCyberRange, the first open, multi-range infrastructure for measuring autonomous cyber attack capability in realistic cyber ranges. It combines 110 vulnerabilities across 15 real web applications and 8 enterprise-like cyber ranges with 156 internal hosts, plus Cage, a toolchain for execution, orchestration, result collection, and verification. The benchmark covers two core stages: web exploitation, where agents explore exposed applications and validate vulnerabilities, and post exploitation, where agents turn an initial foothold into broader internal compromise. We evaluate six frontier AI systems under matched prompts and budgets. GPT-5.5 with Codex performs best, solving 16.1% of web exploitation tasks and 31.7% of post-exploitation tasks; with more concrete hints, these rates increase to 33.0% and 46.3%. We also observe out-of-benchmark findings, including unknown vulnerabilities in popular projects, and payload mutation that bypasses host defenses. These results show that open cyber-range evaluation is necessary for observing emerging offensive capabilities under realistic and reproducible conditions.

cs.CR↗

arXiv2026

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

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 not cross. Within this broader red-line scenario, autonomous penetration represents a core enabling capability and subtask: the ability of LLM-powered AI systems to independently conduct adversarial operations against a target server without human intervention, identify and exploit vulnerabilities, and obtain unauthorized access or control. A growing body of work has sought to assess the autonomous penetration capabilities of AI systems. However, existing evaluations often employ opaque methodologies, rely on unrealistic or overly simplified penetration-testing scenarios, or provide LLMs with excessive prior knowledge and task-specific guidance, and cannot accurately capture the extent to which modern AI systems can autonomously perform this core capability within broader high-impact cyberattack scenarios. To address these limitations, we construct a new autonomous penetration evaluation framework consisting of two components: target servers and agent scaffolding. Specifically, on the target-server side, we design two levels of target environments based on the number of secure services without known vulnerabilities deployed alongside a vulnerable service: Tier~1 (one secure service) and Tier~2 (three secure services), resulting in a total of 300 target servers. Meanwhile, the agent scaffolding adopts a general-purpose agent architecture equipped with a set of general-purpose cybersecurity tools, without any target-specific prior knowledge. We evaluate 19 open-weight and proprietary LLMs, and find that current models achieve penetration success rates ranging from 10.7% to 69.3%. Moreover, we observe that autonomous penetration capability continues to improve alongside advances in overall model capability.

cs.CR↗

arXiv2026

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

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 may lead to privacy leakage, financial loss, or even full system compromise. In this paper, we present AgentGuard, an attribute-based access control framework for tool-use LLM-based agents. AgentGuard adopts a client-server architecture. On the client side, AgentGuard provides lightweight integration for agents implemented in different programming languages and architectures. It requires only minor code modifications (e.g., around 10 lines) without changing the underlying agent execution logic. On the server side, AgentGuard provides three complementary inspection mechanisms to cover both single-tool and cross-tool security risks in agent execution. In addition, it offers a visualized front-end interface for security policy specification and runtime auditing. Currently, AgentGuard is publicly accessible at https://github.com/WhitzardAgent/AgentGuard.

cs.CR↗

arXiv2026

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

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 failure modes. We introduce \textsc{CyberEvolver}, a self-evolving cybersecurity agent framework that iteratively revises its own scaffold based on experience from failed execution attempts. Self-evolution in cybersecurity is challenging because the space of possible scaffold changes is largely unstructured, execution feedback is sparse and often obscured by the environment, and low-diversity updates can cause errors to compound over repeated iterations. \textsc{CyberEvolver} addresses these challenges with a four-layer evolvable agent architecture that decomposes scaffold optimization into structured components, a trace-to-diagnosis mechanism that converts noisy execution logs into actionable revision signals, and a population-based beam search strategy that preserves diverse agent variants during evolution. We evaluate \textsc{CyberEvolver} on CTF challenges, vulnerability exploitation, and penetration-testing tasks using four open-source LLMs. Across these settings, \textsc{CyberEvolver} improves the seed agent's success rate by $13.6$\,\% on average, and outperforms six human-designed cybersecurity agents as well as two self-improvement methods adapted from other domains. These results suggest that scaffold self-evolution is a promising direction for building adaptive LLM agents for security testing.

cs.CR↗

arXiv2026

FlowGuard: Towards Lightweight In-Generation Safety Detection for Diffusion Models via Linear Latent Decoding

Diffusion-based image generation models have advanced rapidly but pose a safety risk due to their potential to generate Not-Safe-For-Work (NSFW) content. Existing NSFW detection methods mainly operate either before or after image generation. Pre-generation methods rely on text prompts and struggle with the gap between prompt safety and image safety. Post-generation methods apply classifiers to final outputs, but they are poorly suited to intermediate noisy images. To address this, we introduce FlowGuard, a cross-model in-generation detection framework that inspects intermediate denoising steps. This is particularly challenging in latent diffusion, where early-stage noise obscures visual signals. FlowGuard employs a novel linear approximation for latent decoding and leverages a curriculum learning approach to stabilize training. By detecting unsafe content early, FlowGuard reduces unnecessary diffusion steps to cut computational costs. Our cross-model benchmark spanning nine diffusion-based backbones shows the effectiveness of FlowGuard for in-generation NSFW detection in both in-distribution and out-of-distribution settings, outperforming existing methods by over 30% in F1 score while delivering transformative efficiency gains, including slashing peak GPU memory demand by over 97% and projection time from 8.1 seconds to 0.2 seconds compared to standard VAE decoding.

cs.CV↗

arXiv2026

Invisible Threats from Model Context Protocol: Generating Stealthy Injection Payload via Tree-based Adaptive Search

Recent advances in the Model Context Protocol (MCP) have enabled large language models (LLMs) to invoke external tools with unprecedented ease. This creates a new class of powerful and tool augmented agents. Unfortunately, this capability also introduces an under explored attack surface, specifically the malicious manipulation of tool responses. Existing techniques for indirect prompt injection that target MCP suffer from high deployment costs, weak semantic coherence, or heavy white box requirements. Furthermore, they are often easily detected by recently proposed defenses. In this paper, we propose Tree structured Injection for Payloads (TIP), a novel black-box attack which generates natural payloads to reliably seize control of MCP enabled agents even under defense. Technically, We cast payload generation as a tree structured search problem and guide the search with an attacker LLM operating under our proposed coarse-to-fine optimization framework. To stabilize learning and avoid local optima, we introduce a path-aware feedback mechanism that surfaces only high quality historical trajectories to the attacker model. The framework is further hardened against defensive transformations by explicitly conditioning the search on observable defense signals and dynamically reallocating the exploration budget. Extensive experiments on four mainstream LLMs show that TIP attains over 95% attack success in undefended settings while requiring an order of magnitude fewer queries than prior adaptive attacks. Against four representative defense approaches, TIP preserves more than 50% effectiveness and significantly outperforms the state-of-the-art attacks. By implementing the attack on real world MCP systems, our results expose an invisible but practical threat vector in MCP deployments. We also discuss potential mitigation approaches to address this critical security gap.

cs.CR↗

arXiv2026

AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk Evaluation

As Large Language Models (LLMs) evolve into autonomous agents, existing safety evaluations face a fundamental trade-off: manual benchmarks are costly, while LLM-based simulators are scalable but suffer from logic hallucination. We present AutoControl Arena, an automated framework for frontier AI risk evaluation built on the principle of logic-narrative decoupling. By grounding deterministic state in executable code while delegating generative dynamics to LLMs, we mitigate hallucination while maintaining flexibility. This principle, instantiated through a three-agent framework, achieves over 98% end-to-end success and 60% human preference over existing simulators. To elicit latent risks, we vary environmental Stress and Temptation across X-Bench (70 scenarios, 7 risk categories). Evaluating 9 frontier models reveals: (1) Alignment Illusion: risk rates surge from 21.7% to 54.5% under pressure, with capable models showing disproportionately larger increases; (2) Scenario-Specific Safety Scaling: advanced reasoning improves robustness for direct harms but worsens it for gaming scenarios; and (3) Divergent Misalignment Patterns: weaker models cause non-malicious harm while stronger models develop strategic concealment.

cs.AI↗

arXiv2026

MirrorGuard: Toward Secure Computer-Use Agents via Simulation-to-Real Reasoning Correction

Large foundation models are integrated into Computer Use Agents (CUAs), enabling autonomous interaction with operating systems through graphical user interfaces (GUIs) to perform complex tasks. This autonomy introduces serious security risks: malicious instructions or visual prompt injections can trigger unsafe reasoning and cause harmful system-level actions. Existing defenses, such as detection-based blocking, prevent damage but often abort tasks prematurely, reducing agent utility. In this paper, we present MirrorGuard, a plug-and-play defense framework that uses simulation-based training to improve CUA security in the real world. To reduce the cost of large-scale training in operating systems, we propose a novel neural-symbolic simulation pipeline, which generates realistic, high-risk GUI interaction trajectories entirely in a text-based simulated environment, which captures unsafe reasoning patterns and potential system hazards without executing real operations. In the simulation environment, MirrorGuard learns to intercept and rectify insecure reasoning chains of CUAs before they produce and execute unsafe actions. In real-world testing, extensive evaluations across diverse benchmarks and CUA architectures show that MirrorGuard significantly mitigates security risks. For instance, on the ByteDance UI-TARS system, it reduces the unsafe rate from 66.5% to 13.0% while maintaining a marginal false refusal rate (FRR). In contrast, the state-of-the-art GuardAgent only achieves a reduction to 53.9% and suffers from a 15.4% higher FRR. Our work proves that simulation-derived defenses can provide robust, real-world protection while maintaining the fundamental utility of the agent. Our code and model are publicly available at https://bmz-q-q.github.io/MirrorGuard/.

cs.AI↗

arXiv2026

WebTrap Park: An Automated Platform for Systematic Security Evaluation of Web Agents

Web Agents are increasingly deployed to perform complex tasks in real web environments, yet their security evaluation remains fragmented and difficult to standardize. We present WebTrap Park, an automated platform for systematic security evaluation of Web Agents through direct observation of their concrete interactions with live web pages. WebTrap Park instantiates three major sources of security risk into 1,226 executable evaluation tasks and enables action based assessment without requiring agent modification. Our results reveal clear security differences across agent frameworks, highlighting the importance of agent architecture beyond the underlying model. WebTrap Park is publicly accessible at https://security.fudan.edu.cn/webagent and provides a scalable foundation for reproducible Web Agent security evaluation.

cs.AI↗

arXiv2026

When Bots Take the Bait: Exposing and Mitigating the Emerging Social Engineering Attack in Web Automation Agent

Web agents, powered by large language models (LLMs), are increasingly deployed to automate complex web interactions. The rise of open-source frameworks (e.g., Browser Use, Skyvern-AI) has accelerated adoption, but also broadened the attack surface. While prior research has focused on model threats such as prompt injection and backdoors, the risks of social engineering remain largely unexplored. We present the first systematic study of social engineering attacks against web automation agents and design a pluggable runtime mitigation solution. On the attack side, we introduce the AgentBait paradigm, which exploits intrinsic weaknesses in agent execution: inducement contexts can distort the agent's reasoning and steer it toward malicious objectives misaligned with the intended task. On the defense side, we propose SUPERVISOR, a lightweight runtime module that enforces environment and intention consistency alignment between webpage context and intended goals to mitigate unsafe operations before execution. Empirical results show that mainstream frameworks are highly vulnerable to AgentBait, with an average attack success rate of 67.5% and peaks above 80% under specific strategies (e.g., trusted identity forgery). Compared with existing lightweight defenses, our module can be seamlessly integrated across different web automation frameworks and reduces attack success rates by up to 78.1% on average while incurring only a 7.7% runtime overhead and preserving usability. This work reveals AgentBait as a critical new threat surface for web agents and establishes a practical, generalizable defense, advancing the security of this rapidly emerging ecosystem. We reported the details of this attack to the framework developers and received acknowledgment before submission.

cs.CR↗

arXiv2025

MCPZoo: A Large-Scale Dataset of Runnable Model Context Protocol Servers for AI Agent

Model Context Protocol (MCP) enables agents to interact with external tools, yet empirical research on MCP is hindered by the lack of large-scale, accessible datasets. We present MCPZoo, the largest and most comprehensive dataset of MCP servers collected from multiple public sources, comprising 129,059 servers (56,053 distinct). MCPZoo includes 16,356 server instances that have been deployed and verified as runnable and interactable, supporting realistic experimentation beyond static analysis. The dataset provides unified metadata and access interfaces, enabling systematic exploration and interaction without manual deployment effort. MCPZoo is released as an open and accessible resource to support research on MCP-based systems and security analysis.

cs.CR↗

arXiv2025

SentinelNet: Safeguarding Multi-Agent Collaboration Through Credit-Based Dynamic Threat Detection

Malicious agents pose significant threats to the reliability and decision-making capabilities of Multi-Agent Systems (MAS) powered by Large Language Models (LLMs). Existing defenses often fall short due to reactive designs or centralized architectures which may introduce single points of failure. To address these challenges, we propose SentinelNet, the first decentralized framework for proactively detecting and mitigating malicious behaviors in multi-agent collaboration. SentinelNet equips each agent with a credit-based detector trained via contrastive learning on augmented adversarial debate trajectories, enabling autonomous evaluation of message credibility and dynamic neighbor ranking via bottom-k elimination to suppress malicious communications. To overcome the scarcity of attack data, it generates adversarial trajectories simulating diverse threats, ensuring robust training. Experiments on MAS benchmarks show SentinelNet achieves near-perfect detection of malicious agents, close to 100% within two debate rounds, and recovers 95% of system accuracy from compromised baselines. By exhibiting strong generalizability across domains and attack patterns, SentinelNet establishes a novel paradigm for safeguarding collaborative MAS.

cs.CR↗

arXiv2025

Shell or Nothing: Real-World Benchmarks and Memory-Activated Agents for Automated Penetration Testing

Penetration testing is critical for identifying and mitigating security vulnerabilities, yet traditional approaches remain expensive, time-consuming, and dependent on expert human labor. Recent work has explored AI-driven pentesting agents, but their evaluation relies on oversimplified capture-the-flag (CTF) settings that embed prior knowledge and reduce complexity, leading to performance estimates far from real-world practice. We close this gap by introducing the first real-world, agent-oriented pentesting benchmark, TermiBench, which shifts the goal from 'flag finding' to achieving full system control. The benchmark spans 510 hosts across 25 services and 30 CVEs, with realistic environments that require autonomous reconnaissance, discrimination between benign and exploitable services, and robust exploit execution. Using this benchmark, we find that existing systems can hardly obtain system shells under realistic conditions. To address these challenges, we propose TermiAgent, a multi-agent penetration testing framework. TermiAgent mitigates long-context forgetting with a Located Memory Activation mechanism and builds a reliable exploit arsenal via structured code understanding rather than naive retrieval. In evaluations, our work outperforms state-of-the-art agents, exhibiting stronger penetration testing capability, reducing execution time and financial cost, and demonstrating practicality even on laptop-scale deployments. Our work delivers both the first open-source benchmark for real-world autonomous pentesting and a novel agent framework that establishes a milestone for AI-driven penetration testing.

cs.CR↗

arXiv2025

PRISON: Unmasking the Criminal Potential of Large Language Models

As large language models (LLMs) advance, concerns about their misconduct in complex social contexts intensify. Existing research overlooked the systematic understanding and assessment of their criminal capability in realistic interactions. We propose a unified framework PRISON, to quantify LLMs' criminal potential across five traits: False Statements, Frame-Up, Psychological Manipulation, Emotional Disguise, and Moral Disengagement. Using structured crime scenarios adapted from classic films grounded in reality, we evaluate both criminal potential and anti-crime ability of LLMs. Results show that state-of-the-art LLMs frequently exhibit emergent criminal tendencies, such as proposing misleading statements or evasion tactics, even without explicit instructions. Moreover, when placed in a detective role, models recognize deceptive behavior with only 44% accuracy on average, revealing a striking mismatch between conducting and detecting criminal behavior. These findings underscore the urgent need for adversarial robustness, behavioral alignment, and safety mechanisms before broader LLM deployment.

cs.CR↗

arXiv2025

Evaluation Faking: Unveiling Observer Effects in Safety Evaluation of Frontier AI Systems

As foundation models grow increasingly more intelligent, reliable and trustworthy safety evaluation becomes more indispensable than ever. However, an important question arises: Whether and how an advanced AI system would perceive the situation of being evaluated, and lead to the broken integrity of the evaluation process? During standard safety tests on a mainstream large reasoning model, we unexpectedly observe that the model without any contextual cues would occasionally recognize it is being evaluated and hence behave more safety-aligned. This motivates us to conduct a systematic study on the phenomenon of evaluation faking, i.e., an AI system autonomously alters its behavior upon recognizing the presence of an evaluation context and thereby influencing the evaluation results. Through extensive experiments on a diverse set of foundation models with mainstream safety benchmarks, we reach the main finding termed the observer effects for AI: When the AI system under evaluation is more advanced in reasoning and situational awareness, the evaluation faking behavior becomes more ubiquitous, which reflects in the following aspects: 1) Reasoning models recognize evaluation 16% more often than non-reasoning models. 2) Scaling foundation models (32B to 671B) increases faking by over 30% in some cases, while smaller models show negligible faking. 3) AI with basic memory is 2.3x more likely to recognize evaluation and scores 19% higher on safety tests (vs. no memory). To measure this, we devised a chain-of-thought monitoring technique to detect faking intent and uncover internal signals correlated with such behavior, offering insights for future mitigation studies.

cs.AI↗

arXiv2025

ReasoningShield: Safety Detection over Reasoning Traces of Large Reasoning Models

Large Reasoning Models (LRMs) leverage transparent reasoning traces, known as Chain-of-Thoughts (CoTs), to break down complex problems into intermediate steps and derive final answers. However, these reasoning traces introduce unique safety challenges: harmful content can be embedded in intermediate steps even when final answers appear benign. Existing moderation tools, designed to handle generated answers, struggle to effectively detect hidden risks within CoTs. To address these challenges, we introduce ReasoningShield, a lightweight yet robust framework for moderating CoTs in LRMs. Our key contributions include: (1) formalizing the task of CoT moderation with a multi-level taxonomy of 10 risk categories across 3 safety levels, (2) creating the first CoT moderation benchmark which contains 9.2K pairs of queries and reasoning traces, including a 7K-sample training set annotated via a human-AI framework and a rigorously curated 2.2K human-annotated test set, and (3) developing a two-stage training strategy that combines stepwise risk analysis and contrastive learning to enhance robustness. Experiments show that ReasoningShield achieves state-of-the-art performance, outperforming task-specific tools like LlamaGuard-4 by 35.6% and general-purpose commercial models like GPT-4o by 15.8% on benchmarks, while also generalizing effectively across diverse reasoning paradigms, tasks, and unseen scenarios. All resources are released at https://github.com/CosmosYi/ReasoningShield.

cs.CL↗

arXiv2025

Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction

LLM-based agents solve complex tasks through iterative reasoning, tool use, and environment interaction, where each intermediate thought directly shapes subsequent actions. Small deviations in these thoughts can therefore propagate into unsafe behaviors, yet existing guardrails typically operate only on final outputs or require intrusive model modifications. We introduce Thought-Aligner, a lightweight plug-in safety model that performs causal correction on unsafe thoughts before action execution, without altering the underlying agent. The corrected thoughts are fed back into the agent, steering its decision process and tool use toward safer trajectories. Because it operates solely at the thought level, Thought-Aligner is model-agnostic and can be integrated into diverse agent frameworks. We train Thought-Aligner via two-stage contrastive learning on paired safe and unsafe thoughts generated across ten risk scenarios. Experiments on diverse agent-safety benchmarks and six LLMs show that Thought-Aligner increases behavioral safety from about 50% without protection to around 90% on average, exceeding state-of-the-art guardrails by roughly 23%, while also improving helpfulness by about 5%. The method incurs low per-step latency and minimal overhead, enabling scalable and practical deployment. We publicly release Thought-Aligner-7B at https://huggingface.co/WhitzardAgent/Thought-Aligner-7B.

cs.AI↗