arXiv subjects

Shujun Li

Publications and source records attributed to Shujun Li.

At least 19 recordsLinked to original sources

arXiv2026

APIOT: Autonomous Vulnerability Management Across Bare-Metal Industrial OT Networks

Operational technology (OT) devices run safety-critical physical processes, yet their security testing remains manual and expert-intensive. Autonomous security agents could ease this burden, but bare-metal OT devices are difficult targets because they lack shells, filesystems, and named exploit abstractions, requiring operation through protocol fields and observable device state. We present APIOT (Autonomous Purple-teaming for Industrial OT), a large language model (LLM) agent framework that completes a discovery -> exploitation -> network-level mitigation -> verification workflow without human intervention. We evaluate APIOT in 360 runs on vulnerable firmware and simulators for Zephyr RTOS, spanning five LLMs, three topologies, two impairment levels, and prompt, tooling and two ablations. APIOT completed 90% of primary missions (63/70 across protocols and topologies) and 85% of 150 cross-model runs (128/150) - feasible across models, with substantial variation. Named exploit tools (e.g., a canned CoAP option-overflow) were faster, but protocol primitives (the agent builds the fields itself) produced more reusable mitigations that blocked unseen payload variants. Runtime oversight improved reliability: success rose from 27/30 to 29/30 with rule-based guards and 30/30 when a second LLM added advisory steering. To our knowledge, this is the first end-to-end autonomous attack-remediation demonstration on bare-metal industrial devices, establishing controlled feasibility - not zero-day discovery or production-OT transfer.

cs.CR↗

arXiv2026

Graphical Models of False Information and Fact Checking Ecosystems

The wide spread of false information online, including misinformation and disinformation, has become a major problem for our highly digitised and globalised society. A lot of research has been done to better understand different aspects of false information online such as behaviours of different actors and patterns of spreading, and also on better detection and prevention of such information using technical and socio-technical means. One major approach to detecting and debunking false information online is to use fact-checkers. Despite a lot of research on online false information, we noticed a lack of conceptual models describing the complicated ecosystem of false information and fact-checking. In this paper, we introduce the first comprehensive graphical model of the ecosystem, focusing on false information online in multiple contexts, including traditional media outlets, as well as user-generated and AI-generated content. The proposed enhanced entity-relationship (EER) model covers a wide range of entities and relationships, and it can be a new useful tool for researchers and practitioners to study false information online and the effects of fact-checking. To demonstrate its usefulness, we provide two example applications of our proposed model, modelling real-world scenarios and reviewing the research literature.

cs.SI↗

arXiv2026

Small, Free, and Effective: Orchestrating Open-Weight Small Language Models to Outperform Single LLM for Malware Analysis

Malware analysis demands rapid interpretation of complex detonation reports spanning filesystem, network, and process behaviours. While large language models (LLMs) demonstrate impressive capabilities for technical artifact interpretation, the opacity and escalating API costs of closed-weight frontier models motivate exploration of open-weight alternatives. However, many open-weight models are large, demanding significant compute resources and incurring non-trivial hosting costs that place them beyond reach for resource-constrained deployments. This paper investigates whether orchestrated ensembles of small language models (SLMs) can match or exceed single LLM performance on structured questions about malware detonation reports. We established baselines by testing eleven open-weight SLMs, three cyber security pre-trained models, and six frontier LLMs on Meta's CyberSecEval Malware Analysis benchmark. We then designed and evaluated four orchestration architectures: (i) a multi-agent pipeline that decomposes analysis into structured evidence-collection and reasoning stages, (ii) an adversarial debate framework in which two agents iteratively critique each other's reasoning, (iii) a hierarchical consultation system that pairs a general-purpose SLM with a cyber-specialised expert model, and (iv) a hybrid architecture that combines evidence-grounded pipelines with adversarial debate reasoning. The hybrid system (Qwen3-4B with Foundation-Sec-8B) achieved 35.30% overall accuracy, exceeding the strongest cyber-specialised baseline (22.54%) and the strongest ungrounded frontier baseline (34.77%); when given the same evidence pipeline, grounded Gemini remained the strongest configuration at 38.22%. These findings show that evidence-grounded orchestration can substantially improve the performance of collaborative SLMs for supporting interpretation of malware detonation reports.

cs.CR↗

arXiv2026

Does Travel Stage Matter? How Leisure Travellers Perceive Their Privacy Attitudes Towards Personal Data Sharing Before, During, and After Travel

People's attitudes towards personal data sharing have been extensively researched, however, limited research studied their evolving nature in across different stages of a leisure trip. This paper addresses this gap by exploring how leisure travellers' attitudes towards sharing personal data change before, during and after travel. Analysing data from an online survey with 318 participants, we found that participants' privacy attitudes towards sharing different personal data vary based on sharing purposes and travel stages. Interestingly, participants exhibited a more relaxed attitude towards sharing commonly sensitive personal data (e.g., name, gender) compared to other types of personal data. This is likely because sharing such data for travel bookings has become essential and widely accepted among travellers when using booking sites, which is in line with previous work stating that information easily obtainable is typically not seen as highly confidential. Moreover, despite participants' self-reported frequent use of social media platforms, content sharing is minimal on TikTok, YouTube, Snapchat, Pinterest, and Twitter. Conversely, Facebook and Instagram were more common for travel-related content sharing. This pattern remains consistent across the three stages of travel, suggesting that the stage of travel does not significantly influence how people share on social media platforms, which has been overlooked in past studies. Furthermore, we discovered that a participant's gender, previous travel frequency, and country of residence can influence their perceptions of personal data sharing at different travel stages, confirming the complex and context-dependent nature of privacy perception and attitudes. Based on the findings observed from this study, we further discuss implications and potential contributions of our work to the privacy and security community in general.

cs.CY↗

arXiv2026

Characterizing Scam-Driven Human Trafficking Across Chinese Borders and Online Community Responses on RedNote

A new form of human trafficking has emerged across Chinese borders, where individuals are lured to Southeast Asia with fraudulent job offers and then coerced into operating online scams. Despite its massive economic and human toll, this scam-driven trafficking remains underexplored in academic research. Through qualitative analysis of 158 RedNote posts, we examined how Chinese online communities respond to this threat. Our findings reveal that perpetrators exploit cultural ties to recruit victims for cybercriminal roles within self-sustaining compounds, using sophisticated manipulation tactics. Survivors face serious reintegration barriers, including family rejection, as the cultural values that enable trafficking also hinder their recovery. While communities present protective strategies, efforts are complicated by doubts about the reliability of support and cross-border coordination. We discuss key implications for prevention, platform governance, and international cooperation against scam-driven trafficking. Warning: This paper contains descriptions of physical, psychological, and sexual abuse.

cs.HC↗

arXiv2026

A Comprehensive Study on GDPR-Oriented Analysis of Privacy Policies: Taxonomy, Corpus and GDPR Concept Classifiers

Machine learning based classifiers that take a privacy policy as the input and predict relevant concepts are useful in different applications such as (semi-)automated compliance analysis against requirements of the EU GDPR. In all past studies, such classifiers produce a concept label per segment (e.g., sentence or paragraph) and their performances were evaluated by using a dataset of labeled segments without considering the privacy policy they belong to. However, such an approach could overestimate the performance in real-world settings, where all segments in a new privacy policy are supposed to be unseen. Additionally, we also observed other research gaps, including the lack of a more complete GDPR taxonomy and the less consideration of hierarchical information in privacy policies. To fill such research gaps, we developed a more complete GDPR taxonomy, created the first corpus of labeled privacy policies with hierarchical information, and conducted the most comprehensive performance evaluation of GDPR concept classifiers for privacy policies. Our work leads to multiple novel findings, including the confirmed inappropriateness of splitting training and test sets at the segment level, the benefits of considering hierarchical information, and the limitations of the "one size fits all" approach, and the significance of testing cross-corpus generalizability.

cs.CR↗

arXiv2026

LADFA: A Framework of Using Large Language Models and Retrieval-Augmented Generation for Personal Data Flow Analysis in Privacy Policies

Privacy policies help inform people about organisations' personal data processing practices, covering different aspects such as data collection, data storage, and sharing of personal data with third parties. Privacy policies are often difficult for people to fully comprehend due to the lengthy and complex legal language used and inconsistent practices across different sectors and organisations. To help conduct automated and large-scale analyses of privacy policies, many researchers have studied applications of machine learning and natural language processing techniques, including large language models (LLMs). While a limited number of prior studies utilised LLMs for extracting personal data flows from privacy policies, our approach builds on this line of work by combining LLMs with retrieval-augmented generation (RAG) and a customised knowledge base derived from existing studies. This paper presents the development of LADFA, an end-to-end computational framework, which can process unstructured text in a given privacy policy, extract personal data flows and construct a personal data flow graph, and conduct analysis of the data flow graph to facilitate insight discovery. The framework consists of a pre-processor, an LLM-based processor, and a data flow post-processor. We demonstrated and validated the effectiveness and accuracy of the proposed approach by conducting a case study that involved examining ten selected privacy policies from the automotive industry. Moreover, it is worth noting that LADFA is designed to be flexible and customisable, making it suitable for a range of text-based analysis tasks beyond privacy policy analysis.

cs.AI↗

arXiv2025

Analysing Safety Risks in LLMs Fine-Tuned with Pseudo-Malicious Cyber Security Data

Large language models (LLMs) have been used in many application domains, including cyber security. The application of LLMs in the cyber security domain presents significant opportunities, such as for enhancing threat analysis and malware detection, but it can also introduce critical risks and safety concerns, including potential personal data leakage and automated generation of new malware. Building on recent findings that fine-tuning LLMs with pseudo-malicious cyber security data significantly compromises their safety, this paper presents a comprehensive validation and extension of these safety risks using a different evaluation framework. We employ the garak red teaming framework with the OWASP Top 10 for LLM Applications to assess four open-source LLMs: Mistral 7B, Llama 3 8B, Gemma 2 9B, and DeepSeek R1 8B. Our evaluation confirms and extends previous findings, showing that fine-tuning reduces safety resilience across all tested LLMs (e.g., the failure rate of Mistral 7B against prompt injection increases from 9.1% to 68.7%). We further propose and evaluate a novel safety alignment approach that carefully rewords instruction-response pairs to include explicit safety precautions and ethical considerations. This work validates previous safety concerns through independent evaluation and introduces new methods for mitigating these risks, contributing towards the development of secure, trustworthy, and ethically aligned LLMs. This approach demonstrates that it is possible to maintain or even improve model safety while preserving technical utility, offering a practical path towards developing safer fine-tuning methodologies.

cs.CR↗

arXiv2025

CyberLLMInstruct: A Pseudo-malicious Dataset Revealing Safety-performance Trade-offs in Cyber Security LLM Fine-tuning

The integration of large language models (LLMs) into cyber security applications presents both opportunities and critical safety risks. We introduce CyberLLMInstruct, a dataset of 54,928 pseudo-malicious instruction-response pairs spanning cyber security tasks including malware analysis, phishing simulations, and zero-day vulnerabilities. Our comprehensive evaluation using seven open-source LLMs reveals a critical trade-off: while fine-tuning improves cyber security task performance (achieving up to 92.50% accuracy on CyberMetric), it severely compromises safety resilience across all tested models and attack vectors (e.g., Llama 3.1 8B's security score against prompt injection drops from 0.95 to 0.15). The dataset incorporates diverse sources including CTF challenges, academic papers, industry reports, and CVE databases to ensure comprehensive coverage of cyber security domains. Our findings highlight the unique challenges of securing LLMs in adversarial domains and establish the critical need for developing fine-tuning methodologies that balance performance gains with safety preservation in security-sensitive domains.

cs.CR↗

arXiv2025

Support or Refute: Analyzing the Stance of Evidence to Detect Out-of-Context Mis- and Disinformation

Mis- and disinformation online have become a major societal problem as major sources of online harms of different kinds. One common form of mis- and disinformation is out-of-context (OOC) information, where different pieces of information are falsely associated, e.g., a real image combined with a false textual caption or a misleading textual description. Although some past studies have attempted to defend against OOC mis- and disinformation through external evidence, they tend to disregard the role of different pieces of evidence with different stances. Motivated by the intuition that the stance of evidence represents a bias towards different detection results, we propose a stance extraction network (SEN) that can extract the stances of different pieces of multi-modal evidence in a unified framework. Moreover, we introduce a support-refutation score calculated based on the co-occurrence relations of named entities into the textual SEN. Extensive experiments on a public large-scale dataset demonstrated that our proposed method outperformed the state-of-the-art baselines, with the best model achieving a performance gain of 3.2% in accuracy. The source code and checkpoints are publicly available at https://github.com/yx3266/SEN.

cs.CL↗

arXiv2025

Cyber Security Educational Games for Children: A Systematic Literature Review

Educational games have been widely used to teach children about cyber security. This systematic literature review reveals evidence of positive learning outcomes, after analysing 91 such games reported in 68 papers published between 2010 and 2024. However, critical gaps have also been identified regarding the design processes and the methodological rigour, including lack of systematic design, misalignment between proposed and achieved learning outcomes, rare use of control groups, limited discussions on ethical considerations, and underutilisation of emerging technologies. We recommend multiple future research directions, e.g., a hybrid approach to game design and evaluation that combines bottom-up and top-down approaches.

cs.CR↗

arXiv2025

Detecting Machine-Generated Texts: Not Just "AI vs Humans" and Explainability is Complicated

As LLMs rapidly advance, increasing concerns arise regarding risks about actual authorship of texts we see online and in real world. The task of distinguishing LLM-authored texts is complicated by the nuanced and overlapping behaviors of both machines and humans. In this paper, we challenge the current practice of considering LLM-generated text detection a binary classification task of differentiating human from AI. Instead, we introduce a novel ternary text classification scheme, adding an "undecided" category for texts that could be attributed to either source, and we show that this new category is crucial to understand how to make the detection result more explainable to lay users. This research shifts the paradigm from merely classifying to explaining machine-generated texts, emphasizing need for detectors to provide clear and understandable explanations to users. Our study involves creating four new datasets comprised of texts from various LLMs and human authors. Based on new datasets, we performed binary classification tests to ascertain the most effective SOTA detection methods and identified SOTA LLMs capable of producing harder-to-detect texts. We constructed a new dataset of texts generated by two top-performing LLMs and human authors, and asked three human annotators to produce ternary labels with explanation notes. This dataset was used to investigate how three top-performing SOTA detectors behave in new ternary classification context. Our results highlight why "undecided" category is much needed from the viewpoint of explainability. Additionally, we conducted an analysis of explainability of the three best-performing detectors and the explanation notes of the human annotators, revealing insights about the complexity of explainable detection of machine-generated texts. Finally, we propose guidelines for developing future detection systems with improved explanatory power.

cs.CL↗

arXiv2025

"I know myself better, but not really greatly": How Well Can LLMs Detect and Explain LLM-Generated Texts?

Distinguishing between human- and LLM-generated texts is crucial given the risks associated with misuse of LLMs. This paper investigates detection and explanation capabilities of current LLMs across two settings: binary (human vs. LLM-generated) and ternary classification (including an ``undecided'' class). We evaluate 6 close- and open-source LLMs of varying sizes and find that self-detection (LLMs identifying their own outputs) consistently outperforms cross-detection (identifying outputs from other LLMs), though both remain suboptimal. Introducing a ternary classification framework improves both detection accuracy and explanation quality across all models. Through comprehensive quantitative and qualitative analyses using our human-annotated dataset, we identify key explanation failures, primarily reliance on inaccurate features, hallucinations, and flawed reasoning. Our findings underscore the limitations of current LLMs in self-detection and self-explanation, highlighting the need for further research to address overfitting and enhance generalizability.

cs.CL↗

arXiv2025

Identity Deepfake Threats to Biometric Authentication Systems: Public and Expert Perspectives

Generative AI (Gen-AI) deepfakes pose a rapidly evolving threat to biometric authentication, yet a significant gap exists between expert understanding of these risks and public perception. This disconnection creates critical vulnerabilities in systems trusted by millions. To bridge this gap, we conducted a comprehensive mixed-method study, surveying 408 professionals across key sectors and conducting in-depth interviews with 37 participants (25 experts, 12 general public [non-experts]). Our findings reveal a paradox: while the public increasingly relies on biometrics for convenience, experts express grave concerns about the spoofing of static modalities like face and voice recognition. We found significant demographic and sector-specific divides in awareness and trust, with finance professionals, for example, showing heightened skepticism. To systematically analyze these threats, we introduce a novel Deepfake Kill Chain model, adapted from Hutchins et al.'s cybersecurity frameworks to map the specific attack vectors used by malicious actors against biometric systems. Based on this model and our empirical findings, we propose a tri-layer mitigation framework that prioritizes dynamic biometric signals (e.g., eye movements), robust privacy-preserving data governance, and targeted educational initiatives. This work provides the first empirically grounded roadmap for defending against AI-generated identity threats by aligning technical safeguards with human-centered insights.

cs.HC↗

arXiv2025

FACTors: A New Dataset for Studying the Fact-checking Ecosystem

Our fight against false information is spearheaded by fact-checkers. They investigate the veracity of claims and document their findings as fact-checking reports. With the rapid increase in the amount of false information circulating online, the use of automation in fact-checking processes aims to strengthen this ecosystem by enhancing scalability. Datasets containing fact-checked claims play a key role in developing such automated solutions. However, to the best of our knowledge, there is no fact-checking dataset at the ecosystem level, covering claims from a sufficiently long period of time and sourced from a wide range of actors reflecting the entire ecosystem that admittedly follows widely-accepted codes and principles of fact-checking. We present a new dataset FACTors, the first to fill this gap by presenting ecosystem-level data on fact-checking. It contains 118,112 claims from 117,993 fact-checking reports in English (co-)authored by 1,953 individuals and published during the period of 1995-2025 by 39 fact-checking organisations that are active signatories of the IFCN (International Fact-Checking Network) and/or EFCSN (European Fact-Checking Standards Network). It contains 7,327 overlapping claims investigated by multiple fact-checking organisations, corresponding to 2,977 unique claims. It allows to conduct new ecosystem-level studies of the fact-checkers (organisations and individuals). To demonstrate the usefulness of FACTors, we present three example applications, including a first-of-its-kind statistical analysis of the fact-checking ecosystem, examining the political inclinations of the fact-checking organisations, and attempting to assign a credibility score to each organisation based on the findings of the statistical analysis and political leanings. Our methods for constructing FACTors are generic and can be used to maintain a live dataset that can be updated dynamically.

cs.IR↗

arXiv2025

A Graph-Based Model for Vehicle-Centric Data Sharing Ecosystem

The development of technologies has prompted a paradigm shift in the automotive industry, with an increasing focus on connected services and autonomous driving capabilities. This transformation allows vehicles to collect and share vast amounts of vehicle-specific and personal data. While these technological advancements offer enhanced user experiences, they also raise privacy concerns. To understand the ecosystem of data collection and sharing in modern vehicles, we adopted the ontology 101 methodology to incorporate information extracted from different sources, including analysis of privacy policies using GPT-4, a small-scale systematic literature review, and an existing ontology, to develop a high-level conceptual graph-based model, aiming to get insights into how modern vehicles handle data exchange among different parties. This serves as a foundational model with the flexibility and scalability to further expand for modelling and analysing data sharing practices across diverse contexts. Two realistic examples were developed to demonstrate the usefulness and effectiveness of discovering insights into privacy regarding vehicle-related data sharing. We also recommend several future research directions, such as exploring advanced ontology languages for reasoning tasks, supporting topological analysis for discovering data privacy risks/concerns, and developing useful tools for comparative analysis, to strengthen the understanding of the vehicle-centric data sharing ecosystem.

cs.SI↗

arXiv2025

SE#PCFG: Semantically Enhanced PCFG for Password Analysis and Cracking

Much research has been done on user-generated textual passwords. Surprisingly, semantic information in such passwords remain under-investigated, with passwords created by English- and/or Chinese-speaking users being more studied with limited semantics. This paper fills this gap by proposing a general framework based on semantically enhanced PCFG (probabilistic context-free grammars) named SE#PCFG. It allowed us to consider 43 types of semantic information, the richest set considered so far, for password analysis. Applying SE#PCFG to 17 large leaked password databases of user speaking four languages (English, Chinese, German and French), we demonstrate its usefulness and report a wide range of new insights about password semantics at different levels such as cross-website password correlations. Furthermore, based on SE#PCFG and a new systematic smoothing method, we proposed the Semantically Enhanced Password Cracking Architecture (SEPCA), and compared its performance against three SOTA (state-of-the-art) benchmarks in terms of the password coverage rate: two other PCFG variants and neural network. Our experimental results showed that SEPCA outperformed all the three benchmarks consistently and significantly across 52 test cases, by up to 21.53%, 52.55% and 7.86%, respectively, at the user-level (with duplicate passwords). At the level of unique passwords, SEPCA also beats the three counterparts by up to 43.83%, 94.11% and 11.16%, respectively.

cs.CR↗

arXiv2025

Using Anomaly Detection to Detect Poisoning Attacks in Federated Learning Applications

Adversarial attacks such as poisoning attacks have attracted the attention of many machine learning researchers. Traditionally, poisoning attacks attempt to inject adversarial training data in order to manipulate the trained model. In federated learning (FL), data poisoning attacks can be generalized to model poisoning attacks, which cannot be detected by simpler methods due to the lack of access to local training data by the detector. State-of-the-art poisoning attack detection methods for FL have various weaknesses, e.g., the number of attackers has to be known or not high enough, working with i.i.d. data only, and high computational complexity. To overcome above weaknesses, we propose a novel framework for detecting poisoning attacks in FL, which employs a reference model based on a public dataset and an auditor model to detect malicious updates. We implemented a detector based on the proposed framework and using a one-class support vector machine (OC-SVM), which reaches the lowest possible computational complexity O(K) where K is the number of clients. We evaluated our detector's performance against state-of-the-art (SOTA) poisoning attacks for two typical applications of FL: electrocardiograph (ECG) classification and human activity recognition (HAR). Our experimental results validated the performance of our detector over other SOTA detection methods.

cs.LG↗