arXiv subjects

Guanhua Yan

Publications and source records attributed to Guanhua Yan.

5 recordsLinked to original sources

arXiv2026

Benchmarking LLM-Assisted Blue Teaming via Standardized Threat Hunting

As cyber threats continue to grow in scale and sophistication, blue team defenders increasingly require advanced tools to proactively detect and mitigate risks. Large Language Models (LLMs) offer promising capabilities for enhancing threat analysis. However, their effectiveness in real-world blue team threat-hunting scenarios remains insufficiently explored. This paper presents CyberTeam, a benchmark designed to guide LLMs in blue teaming practice. CyberTeam constructs a standardized workflow in two stages. First, it models realistic threat-hunting workflows by capturing the dependencies among analytical tasks from threat attribution to incident response. Next, each task is addressed through a set of operational modules tailored to its specific analytical requirements. This transforms threat hunting into a structured sequence of reasoning steps, with each step grounded in a discrete operation and ordered according to task-specific dependencies. Guided by this framework, LLMs are directed to perform threat-hunting tasks through modularized steps. Overall, CyberTeam integrates 30 tasks and 9 operational modules to guide LLMs through standardized threat analysis. We evaluate both leading LLMs and state-of-the-art cybersecurity agents, comparing CyberTeam against open-ended reasoning strategies. Our results highlight the improvements enabled by standardized design, while also revealing the limitations of open-ended reasoning in real-world threat hunting.

cs.CR↗

arXiv2026

Uncovering Vulnerabilities of LLM-Assisted Cyber Threat Intelligence

Large language models (LLMs) are increasingly used to help security analysts manage the surge of cyber threats, automating tasks from vulnerability assessment to incident response. Yet in operational CTI workflows, reliability gaps remain substantial. Existing explanations often point to generic model issues (e.g., hallucination), but we argue the dominant bottleneck is the threat landscape itself: CTI is heterogeneous, volatile, and fragmented. Under these conditions, evidence is intertwined, crowdsourced, and temporally unstable, which are properties that standard LLM-based studies rarely capture. In this paper, we present a comprehensive empirical study of LLM vulnerabilities in CTI reasoning. We introduce a human-in-the-loop categorization framework that robustly labels failure modes across the CTI lifecycle, avoiding the brittleness of automated "LLM-as-a-judge" pipelines. We identify three domain-specific cognitive failures: spurious correlations from superficial metadata, contradictory knowledge from conflicting sources, and constrained generalization to emerging threats. We validate these mechanisms via causal interventions and show that targeted defenses reduce failure rates significantly. Together, these results offer a concrete roadmap for building resilient, domain-aware CTI agents.

cs.CR↗

arXiv2025

Benchmarking LLMs in an Embodied Environment for Blue Team Threat Hunting

As cyber threats continue to grow in scale and sophistication, blue team defenders increasingly require advanced tools to proactively detect and mitigate risks. Large Language Models (LLMs) offer promising capabilities for enhancing threat analysis. However, their effectiveness in real-world blue team threat-hunting scenarios remains insufficiently explored. In this paper, we present CYBERTEAM, a benchmark designed to guide LLMs in blue teaming practice. CYBERTEAM constructs an embodied environment in two stages. First, it models realistic threat-hunting workflows by capturing the dependencies among analytical tasks from threat attribution to incident response. Next, each task is addressed through a set of embodied functions tailored to its specific analytical requirements. This transforms the overall threat-hunting process into a structured sequence of function-driven operations, where each node represents a discrete function and edges define the execution order. Guided by this framework, LLMs are directed to perform threat-hunting tasks through modular steps. Overall, CYBERTEAM integrates 30 tasks and 9 embodied functions, guiding LLMs through pipelined threat analysis. We evaluate leading LLMs and state-of-the-art cybersecurity agents, comparing CYBERTEAM's embodied function-calling against fundamental elicitation strategies. Our results offer valuable insights into the current capabilities and limitations of LLMs in threat hunting, laying the foundation for the practical adoption in real-world cybersecurity applications.

cs.CR↗

arXiv2016

The Rise of Social Botnets: Attacks and Countermeasures

Online social networks (OSNs) are increasingly threatened by social bots which are software-controlled OSN accounts that mimic human users with malicious intentions. A social botnet refers to a group of social bots under the control of a single botmaster, which collaborate to conduct malicious behavior while mimicking the interactions among normal OSN users to reduce their individual risk of being detected. We demonstrate the effectiveness and advantages of exploiting a social botnet for spam distribution and digital-influence manipulation through real experiments on Twitter and also trace-driven simulations. We also propose the corresponding countermeasures and evaluate their effectiveness. Our results can help understand the potentially detrimental effects of social botnets and help OSNs improve their bot(net) detection systems.

cs.SI↗

arXiv2013

Containing Viral Spread on Sparse Random Graphs: Bounds, Algorithms, and Experiments

Viral spread on large graphs has many real-life applications such as malware propagation in computer networks and rumor (or misinformation) spread in Twitter-like online social networks. Although viral spread on large graphs has been intensively analyzed on classical models such as Susceptible-Infectious-Recovered, there still exits a deficit of effective methods in practice to contain epidemic spread once it passes a critical threshold. Against this backdrop, we explore methods of containing viral spread in large networks with the focus on sparse random networks. The viral containment strategy is to partition a large network into small components and then to ensure the sanity of all messages delivered across different components. With such a defense mechanism in place, an epidemic spread starting from any node is limited to only those nodes belonging to the same component as the initial infection node. We establish both lower and upper bounds on the costs of inspecting inter-component messages. We further propose heuristic-based approaches to partition large input graphs into small components. Finally, we study the performance of our proposed algorithms under different network topologies and different edge weight models.

math.PR↗