arXiv subjects

Ge Chu

Publications and source records attributed to Ge Chu.

4 recordsLinked to original sources

arXiv2026

Decoupling Reconnaissance and Exploitation: Measuring the Capability Boundaries of LLM-Based Web Penetration Testing

Large Language Models (LLMs) have shown promise for automated penetration testing, yet existing end-to-end black-box evaluations are highly susceptible to error cascading: failures in early reconnaissance can mask an agent's actual ability to exploit vulnerabilities. To more accurately characterize these capabilities, we propose a two-stage decoupled evaluation framework that separates exploit execution from reconnaissance. Using ground-truth injection and knowledge-driven ablation across 70 high-fidelity web vulnerability testbeds, our framework isolates exploitation performance from reconnaissance noise. We empirically evaluate five open-source penetration-testing agents, covering multiagent, monolithic, and graph-driven architectures, on a strictly aligned subset of 50 representative vulnerabilities. The results reveal a substantial capability gap. With accurate vulnerability context, agents achieve a functional success rate of up to 90.0%, whereas autonomous reconnaissance, measured by targeted vulnerability recall, plateaus at approximately 50.0%, primarily due to failures in parsing unstructured telemetry. Cross-architectural analysis further reveals distinct capability niches: multi-agent isolation is more effective for long-sequence interactions such as de-serialization, while monolithic and graph-driven designs perform better on short-chain injections and cross-session access-control vulnerabilities, respectively. This decoupled evaluation work provides a fine-grained benchmarking protocol and an empirical basis for designing next-generation automated offensive security agents.

cs.CR↗

arXiv2026

MACAA: Belief-Revision Multi-Agent Reasoning for Code Authorship Verification

Code authorship attribution (CAA) supports software forensics, plagiarism detection, and intellectual property protection. However, existing supervised CAA approaches suffer from scarce training data and closed-world assumptions: they require sufficient labeled code from fixed candidate-author sets, making training difficult in low-data cases and predictions unreliable for open-world test pairs with unseen samples, or heterogeneous code pairs. Large language models remove task-specific training, but direct prompting depends on costly expert-designed prompts, can hallucinate over complex heterogeneous code pairs, and rarely yields auditable evidence traces. We propose MACAA, a belief-revision-based multi-agent framework for training-free code authorship verification. MACAA comprises a Coordinator and four Expert Agents analyzing layout, lexical, syntactic, and programming-pattern evidence. The Coordinator gathers expert signals for expansion, discounts unreliable evidence through contraction, and resolves conflicts through revision to preserve belief consistency, replacing direct LLM judgment with auditable hypothesis refinement. MACAA achieves 89.15\% F1 on same-language benchmarks and 80.00\% on mixed cross-language pairs, outperforming the baselines overall in both same-language and cross-language evaluations.

cs.SE↗

arXiv2025

LogICL: Distilling LLM Reasoning to Bridge the Semantic Gap in Cross-Domain Log Anomaly Detection

Effective log anomaly detection is critical to sustaining reliability in large-scale IT infrastructures. Transformer-based models require substantial resources and labeled data, exacerbating the cold-start problem in target domains where logs are scarce. Existing cross-domain methods leverage source logs but struggle with generalization due to reliance on surface lexical similarity, failing to capture latent semantic equivalence amid structural divergences. To address this, we propose LogICL, a framework distilling Large Language Model (LLM) reasoning into a lightweight encoder for cross-domain anomaly detection. During training, LogICL constructs a delta matrix measuring the utility of demonstrations selected via Maximal Marginal Relevance relative to zero-shot inference. The encoder is optimized via a multi-objective loss comprising an ICL-Guided term that aligns representations based on reasoning assistance utility, maximum mean discrepancy for domain alignment, and supervised contrastive loss. At inference, the optimized encoder retrieves reasoning-aware demonstrations using semantic similarity and delta scores, enabling frozen-LLM in-context learning with Chain-of-Thought for accurate and interpretable detection. Experiments on few-shot and zero-shot cross-domain benchmarks confirm LogICL achieves state-of-the-art performance across heterogeneous systems. Further analysis via visualizations and case studies confirms LogICL bridges the semantic gap beyond surface lexical similarity, effectively capturing latent semantic equivalence for rapid deployment.

cs.SE↗

arXiv2019

Agent-based (BDI) modeling for automation of penetration testing

Penetration testing (or pentesting) is one of the widely used and important methodologies to assess the security of computer systems and networks. Traditional pentesting relies on the domain expert knowledge and requires considerable human effort all of which incurs a high cost. The automation can significantly improve the efficiency, availability and lower the cost of penetration testing. Existing approaches to the automation include those which map vulnerability scanner results to the corresponding exploit tools, and those addressing the pentesting as a planning problem expressed in terms of attack graphs. Due to mainly non-interactive processing, such solutions can deal effectively only with static and simple targets. In this paper, we propose an automated penetration testing approach based on the belief-desire-intention (BDI) agent model, which is central in the research on agent-based processing in that it deals interactively with dynamic, uncertain and complex environments. Penetration testing actions are defined as a series of BDI plans and the BDI reasoning cycle is used to represent the penetration testing process. The model is extensible and new plans can be added, once they have been elicited from the human experts. We report on the results of testing of proof of concept BDI-based penetration testing tool in the simulated environment.

cs.CR↗