arXiv subjects

Geng Hong

Publications and source records attributed to Geng Hong.

32 records · Page 2Linked to original sources

arXiv2026

Unveiling the Resilience of LLM-Enhanced Search Engines against Black-Hat SEO Manipulation

The emergence of Large Language Model-enhanced Search Engines (LLMSEs) has revolutionized information retrieval by integrating web-scale search capabilities with AI-powered summarization. While these systems demonstrate improved efficiency over traditional search engines, their security implications against well-established black-hat Search Engine Optimization (SEO) attacks remain unexplored. In this paper, we present the first systematic study of SEO attacks targeting LLMSEs. Specifically, we examine ten representative LLMSE products (e.g., ChatGPT, Gemini) and construct SEO-Bench, a benchmark comprising 1,000 real-world black-hat SEO websites, to evaluate both open- and closed-source LLMSEs. Our measurements show that LLMSEs mitigate over 99.78% of traditional SEO attacks, with the phase of retrieval serving as the primary filter, intercepting the vast majority of malicious queries. We further propose and evaluate seven LLMSEO attack strategies, demonstrating that off-the-shelf LLMSEs are vulnerable to LLMSEO attacks, i.e., rewritten-query stuffing and segmented texts double the manipulation rate compared to the baseline. This work offers the first in-depth security analysis of the LLMSE ecosystem, providing practical insights for building more resilient AI-driven search systems. We have responsibly reported the identified issues to major vendors.

cs.CR↗

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

OpenDeception: Learning Deception and Trust in Human-AI Interaction via Multi-Agent Simulation

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 scenario-specific and model-centric. We introduce OpenDeception, a lightweight framework for jointly evaluating deception risk from both sides of human-AI dialogue. It consists of a scenario benchmark with 50 real-world deception cases, an IntentNet that infers deceptive intent from agent reasoning, and a TrustNet that estimates user susceptibility. To address data scarcity, we synthesize high-risk dialogues via LLM-based role-and-goal simulation, and train the User Trust Scorer using contrastive learning on controlled response pairs, avoiding unreliable scalar labels. Experiments on 11 LLMs and three large reasoning models show that over 90% of goal-driven interactions in most models exhibit deceptive intent, with stronger models displaying higher risk. A real-world case study adapted from a documented AI-induced suicide incident further demonstrates that our joint evaluation can proactively trigger warnings before critical trust thresholds are reached.

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

SmartSight: Mitigating Hallucination in Video-LLMs Without Compromising Video Understanding via Temporal Attention Collapse

Despite Video Large Language Models having rapidly advanced in recent years, perceptual hallucinations pose a substantial safety risk, which severely restricts their real-world applicability. While several methods for hallucination mitigation have been proposed, they often compromise the model's capacity for video understanding and reasoning. In this work, we propose SmartSight, a pioneering step to address this issue in a training-free manner by leveraging the model's own introspective capabilities. Specifically, SmartSight generates multiple candidate responses to uncover low-hallucinated outputs that are often obscured by standard greedy decoding. It assesses the hallucination of each response using the Temporal Attention Collapse score, which measures whether the model over-focuses on trivial temporal regions of the input video when generating the response. To improve efficiency, SmartSight identifies the Visual Attention Vanishing point, enabling more accurate hallucination estimation and early termination of hallucinated responses, leading to a substantial reduction in decoding cost. Experiments show that SmartSight substantially lowers hallucinations for Qwen2.5-VL-7B by 10.59% on VRIPT-HAL, while simultaneously enhancing video understanding and reasoning, boosting performance on VideoMMMU by up to 8.86%. These results highlight SmartSight's effectiveness in improving the reliability of open-source Video-LLMs.

cs.CV↗

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

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

Feedback-Guided Extraction of Knowledge Base from Retrieval-Augmented LLM Applications

Retrieval-Augmented Generation (RAG) expands the knowledge boundary of large language models (LLMs) by integrating external knowledge bases, whose construction is often time-consuming and laborious. If an adversary extracts the knowledge base verbatim, it not only severely infringes the owner's intellectual property but also enables the adversary to replicate the application's functionality for unfair competition. Previous works on knowledge base extraction are limited either by low extraction coverage (usually less than 4%) in query-based attacks or by impractical assumptions of white-box access in embedding-based optimization methods. In this work, we propose CopyBreakRAG, an agent-based black-box attack that reasons from feedback and adaptively generates new adversarial queries for progressive extraction. By balancing exploration and exploitation through curiosity-driven queries and feedback-guided query refinement, our method overcomes the limitations of prior approaches and achieves significantly higher extraction coverage in realistic black-box settings. Experimental results show that CopyBreakRAG outperforms the state-of-the-art black-box approach by 45% on average in terms of chunk extraction ratio from applications built with mainstream RAG frameworks, and extracts over 70% of the data from the knowledge base in applications on commercial platforms including OpenAI's GPTs and ByteDance's Coze when essential protection is in place.

cs.CR↗

arXiv2025

The Illusionist's Prompt: Exposing the Factual Vulnerabilities of Large Language Models with Linguistic Nuances

As Large Language Models (LLMs) continue to advance, they are increasingly relied upon as real-time sources of information by non-expert users. To ensure the factuality of the information they provide, much research has focused on mitigating hallucinations in LLM responses, but only in the context of formal user queries, rather than maliciously crafted ones. In this study, we introduce The Illusionist's Prompt, a novel hallucination attack that incorporates linguistic nuances into adversarial queries, challenging the factual accuracy of LLMs against five types of fact-enhancing strategies. Our attack automatically generates highly transferrable illusory prompts to induce internal factual errors, all while preserving user intent and semantics. Extensive experiments confirm the effectiveness of our attack in compromising black-box LLMs, including commercial APIs like GPT-4o and Gemini-2.0, even with various defensive mechanisms.

cs.CL↗

arXiv2025

You Can't Eat Your Cake and Have It Too: The Performance Degradation of LLMs with Jailbreak Defense

With the rise of generative large language models (LLMs) like LLaMA and ChatGPT, these models have significantly transformed daily life and work by providing advanced insights. However, as jailbreak attacks continue to circumvent built-in safety mechanisms, exploiting carefully crafted scenarios or tokens, the safety risks of LLMs have come into focus. While numerous defense strategies--such as prompt detection, modification, and model fine-tuning--have been proposed to counter these attacks, a critical question arises: do these defenses compromise the utility and usability of LLMs for legitimate users? Existing research predominantly focuses on the effectiveness of defense strategies without thoroughly examining their impact on performance, leaving a gap in understanding the trade-offs between LLM safety and performance. Our research addresses this gap by conducting a comprehensive study on the utility degradation, safety elevation, and exaggerated-safety escalation of LLMs with jailbreak defense strategies. We propose USEBench, a novel benchmark designed to evaluate these aspects, along with USEIndex, a comprehensive metric for assessing overall model performance. Through experiments on seven state-of-the-art LLMs, we found that mainstream jailbreak defenses fail to ensure both safety and performance simultaneously. Although model-finetuning performs the best overall, their effectiveness varies across LLMs. Furthermore, vertical comparisons reveal that developers commonly prioritize performance over safety when iterating or fine-tuning their LLMs.

cs.CR↗

arXiv2024

Revealing the Black Box of Device Search Engine: Scanning Assets, Strategies, and Ethical Consideration

In the digital age, device search engines such as Censys and Shodan play crucial roles by scanning the internet to catalog online devices, aiding in the understanding and mitigation of network security risks. While previous research has used these tools to detect devices and assess vulnerabilities, there remains uncertainty regarding the assets they scan, the strategies they employ, and whether they adhere to ethical guidelines. This study presents the first comprehensive examination of these engines' operational and ethical dimensions. We developed a novel framework to trace the IP addresses utilized by these engines and collected 1,407 scanner IPs. By uncovering their IPs, we gain deep insights into the actions of device search engines for the first time and gain original findings. By employing 28 honeypots to monitor their scanning activities extensively in one year, we demonstrate that users can hardly evade scans by blocklisting scanner IPs or migrating service ports. Our findings reveal significant ethical concerns, including a lack of transparency, harmlessness, and anonymity. Notably, these engines often fail to provide transparency and do not allow users to opt out of scans. Further, the engines send malformed requests, attempt to access excessive details without authorization, and even publish personally identifiable information (PII) and screenshots on search results. These practices compromise user privacy and expose devices to further risks by potentially aiding malicious entities. This paper emphasizes the urgent need for stricter ethical standards and enhanced transparency in the operations of device search engines, offering crucial insights into safeguarding against invasive scanning practices and protecting digital infrastructures.

cs.CR↗