arXiv subjects

Jin B. Hong

Publications and source records attributed to Jin B. Hong.

15 recordsLinked to original sources

arXiv2026

ClueWeaver: Reward-Guided Dual-Agent Evidence Reasoning for Compact LLMs on Literary Long Narratives

Humanities and social science research requires close reading of long narrative materials such as novels, scripts, archives, and case reports, yet many users have limited access to costly proprietary long-context models. Compact, locally deployable language models are a practical alternative, but directly feeding them an entire long context remains costly, hard to inspect, and prone to missing sparse evidence. We present ClueWeaver, an evidence-aware dual-agent framework for long-narrative question answering with compact local models. A Finder identifies passages containing answer-critical clues through retrieval-guided segmentation, while an Interpreter derives the answer from the selected evidence, produces rationales with paragraph-ID citations, and applies an internal self-calibration pass for high-risk questions. Both agents are optimized with reward-guided reinforcement learning: Finder rewards emphasize evidence retention and faithful paragraph-ID references, and Interpreter rewards emphasize correctness, grounding, and concise explanations. This decomposition makes evidence selection and reasoning more inspectable than end-to-end prompting. Experiments across multiple long-context narrative question answering and claim verification settings show that ClueWeaver substantially improves local end-to-end language models while providing evidence coverage and paragraph-referenced reasoning traces. Code is available at https://github.com/Ameame1/ClueWeaver.

cs.CL↗

arXiv2026

MIRAGE: How Conversation State Shapes Historical Evidence Use in Multimodal Personal Agents

Multimodal large language model (MLLM) agents are increasingly used as personal assistants for long-running tasks. Their utility depends on continuity: agents must retrieve and use earlier evidence across dialogue, files, and workspace state. However, agents can generate plausible answers even when access to that history has degraded, causing outcome-only evaluation to overestimate true evidence use. We present MIRAGE (Multimodal Interaction Retrieval, Attribution, and Grounding Evaluation), a controlled study of historical evidence use under conversation-state variation in multimodal personal agents. MIRAGE holds evidence objects, questions, and scoring fixed while varying only conversation state, and evaluates whether an agent can determine answerability, recover the correct source, and answer from it. Across seven frontier and open-weight multimodal backbones, we find that: 1) pre-compaction depth and post-compaction continuation form distinct, non-monotonic failure regimes rather than a single degradation curve; 2) open-weight models rely heavily on context continuity and are reluctant to spontaneously switch to tool-mediated retrieval when provenance fails; and 3) retrieval pressure improves source attribution in deep pre-compaction states for tool-compliant models, but consistently regresses after compaction, where stored evidence has already degraded. These findings show that historical evidence use should be evaluated under state variation, rather than inferred from outcome-only correctness.

cs.CL↗

arXiv2026

CARE: Pre-Execution Command Verification for Shell-Executing LLM Agents

Large Language Model (LLM) agents are increasingly used for coding and terminal automation, making shell-command dispatch a high-stakes runtime control point. We study command-level pre-execution mediation for individual shell commands produced by LLM agents under bounded path context. Existing safeguards remain limited: generic guardrails do not model shell structure in sufficient detail, always-on LLM judges are relatively costly and variable, and shell parsers do not directly prevent harmful execution. We present CARE (Canonicalization, Attribution, and Resolution Engine), a shell-specific, static-first verifier for individual shell commands before execution. CARE canonicalizes generated commands into stable verification targets, derives deterministic evidence over syntax, command semantics, path context, and provenance-backed risk patterns, and escalates only underdetermined cases to an LLM judge. This design keeps the common case fast, reproducible, and auditable while reserving neural adjudication for borderline commands. On the balanced main split, CARE reaches 85.64% F1 with a 0.91% false-positive rate at 2.32 ms mean latency. When deployed in its static enforcement profile, CARE retains 84.99% F1 at 0.34 ms and reduces realised harm on RedCode-gen to 37.33%. Across external-generalization tests and controlled Docker-sandbox execution, these profiles expose a practical trade-off between benign recovery, false-positive burden, latency, and harm reduction. Overall, command-level shell mediation can reduce dispatch-boundary risk for LLM agents while preserving most benign workflows.

cs.CR↗

arXiv2026

Does Faithfulness-Guided Alignment Hurt Accuracy? Unlocking Accurate and Faithful Post-Retrieval Reasoning

Retrieval-augmented generation (RAG) can achieve strong answer accuracy on multi-hop questions, but outcome-level rewards often leave reasoning traces weakly grounded and difficult to audit. Under noisy retrieval, models may exhibit right-answer-wrong-reason failures, where the final answer is correct but the supporting rationale exploits shortcuts or unsupported evidence. We therefore ask whether faithfulness-guided alignment hurts answer accuracy in post-retrieval reasoning. To study this question, we propose CRAFT (Calibrated Reasoning with Answer-Faithful Traces), a reinforcement learning framework for the response-generation stage of retrieval-augmented multi-hop question answering. CRAFT trains models to produce structured reasoning traces with configurable auditability, while combining deterministic rewards for format compliance, answer correctness, and citation validity with a judge-based reward for semantic faithfulness. Experiments across model scales and benchmarks show that CRAFT unlocks task-specific reasoning capacity from 1.5B upward, improving both answer accuracy and Faithfulness; at 0.5B, performance remains sharply template-dependent. At 7B, CRAFT improves Faithfulness over the Base model in all evaluated settings and remains competitive with strong closed-source models. Code is available at https://github.com/Ameame1/CRAFT.

cs.CL↗

arXiv2026

When the Same Musical Knowledge Forgets Differently: A Clean Probe of Pathway-Dependent Forgetting

A model can learn that the piano piece Für Elise is calm and reflective by listening to the audio or by reading a text description, but does it matter which route that knowledge took when it is later at risk of being forgotten? Forgetting research in multimodal models measures what knowledge is lost under adaptation, yet has not asked whether acquisition route affects how easily that knowledge is forgotten. We call this untested premise the Pathway-Invariant Assumption. Music understanding enables a clean test because a music clip and a canonical text description can be aligned to the same perceptual content, allowing the same knowledge unit to enter a model through listening or reading while the target remains fixed. Across multiple architecturally distinct audio-language models, we observe a consistent asymmetry: text-pathway knowledge is forgotten more than matched audio-pathway knowledge under identical adaptation pressure. To attribute this effect to route rather than confounds, we introduce the Paired Pathway Controlled Protocol (PPCP), a three-phase design that establishes matched pathway baselines, activates both pathways under symmetric supervision on the same knowledge pool, and applies identical forgetting pressure to both pathways. The gap is stable across models and gain-controlled analyses, persists when contradictory overwrite is replaced by correct-label cross-domain learning, remains under single-modality pressure, and is not removed by lightweight replay. Two independent routing-depth controls confirm that the effect is not explained by architectural depth, pointing to input representation as the dominant factor. Under PPCP, our results demonstrate that forgetting is highly route-dependent, establishing acquisition route as a new analytical dimension for forgetting research and multimodal system design.

cs.SD↗

arXiv2026

STIndex: A Context-Aware Multi-Dimensional Spatiotemporal Information Extraction System

Extracting structured knowledge from unstructured data still faces practical limitations: entity and event extraction pipelines remain brittle, knowledge graph construction requires costly ontology engineering, and cross-domain generalization is rarely production-ready. In contrast, space and time provide universal contextual anchors that naturally align heterogeneous information and benefit downstream tasks such as retrieval and reasoning. We introduce \textbf{STIndex}, an end-to-end system that structures unstructured content into a multidimensional spatiotemporal data warehouse. Users define domain-specific analysis dimensions with configurable hierarchies, while large language models perform context-aware extraction and grounding. \textbf{STIndex} integrates document-level memory, geocoding correction, and quality validation, and offers an interactive analytics dashboard for visualization, clustering, burst detection, and entity network analysis. In evaluation on a public health benchmark, \textbf{STIndex} improves spatiotemporal entity extraction F1 by 4.37\% (GPT-4o-mini) and 3.60\% (Qwen3-8B). A live demonstration and open-source code are available at https://stindex.ai4wa.com/dashboard.

cs.DB↗

arXiv2026

PRISMA: Reinforcement Learning Guided Two-Stage Policy Optimization in Multi-Agent Architecture for Open-Domain Multi-Hop Question Answering

Answering real-world open-domain multi-hop questions over massive corpora is a critical challenge in Retrieval-Augmented Generation (RAG) systems. Recent research employs reinforcement learning (RL) to end-to-end optimize the retrieval-augmented reasoning process, directly enhancing its capacity to resolve complex queries. However, reliable deployment is hindered by two obstacles. 1) Retrieval Collapse: iterative retrieval over large corpora fails to locate intermediate evidence containing bridge answers without reasoning-guided planning, causing downstream reasoning to collapse. 2) Learning Instability: end-to-end trajectory training suffers from weak credit assignment across reasoning chains and poor error localization across modules, causing overfitting to benchmark-specific heuristics that limit transferability and stability. To address these problems, we propose PRISMA, a decoupled RL-guided framework featuring a Plan-Retrieve-Inspect-Solve-Memoize architecture. PRISMA's strength lies in reasoning-guided collaboration: the Inspector provides reasoning-based feedback to refine the Planner's decomposition and fine-grained retrieval, while enforcing evidence-grounded reasoning in the Solver. We optimize individual agent capabilities via Two-Stage Group Relative Policy Optimization (GRPO). Stage I calibrates the Planner and Solver as specialized experts in planning and reasoning, while Stage II utilizes Observation-Aware Residual Policy Optimization (OARPO) to enhance the Inspector's ability to verify context and trigger targeted recovery. Experiments show that PRISMA achieves state-of-the-art performance on ten benchmarks and can be deployed efficiently in real-world scenarios.

cs.AI↗

arXiv2025

Enhancing Reliability in LLM-Integrated Robotic Systems: A Unified Approach to Security and Safety

Integrating large language models (LLMs) into robotic systems has revolutionised embodied artificial intelligence, enabling advanced decision-making and adaptability. However, ensuring reliability, encompassing both security against adversarial attacks and safety in complex environments, remains a critical challenge. To address this, we propose a unified framework that mitigates prompt injection attacks while enforcing operational safety through robust validation mechanisms. Our approach combines prompt assembling, state management, and safety validation, evaluated using both performance and security metrics. Experiments show a 30.8% improvement under injection attacks and up to a 325% improvement in complex environment settings under adversarial conditions compared to baseline scenarios. This work bridges the gap between safety and security in LLM-based robotic systems, offering actionable insights for deploying reliable LLM-integrated mobile robots in real-world settings. The framework is open-sourced with simulation and physical deployment demos at https://llmeyesim.vercel.app/

cs.RO↗

arXiv2025

Empowering IoT Firmware Secure Update with Customization Rights

Firmware updates remain the primary line of defense for IoT devices; however, the update channel itself has become a well-established attack vector. Existing defenses mainly focus on securing monolithic firmware images, leaving module-level customization -a growing user demand-largely unprotected and insufficiently explored. To address this gap, we conduct a pilot study on the update workflows of 200 Linux-based IoT devices across 23 vendors, uncovering five previously undocumented vulnerabilities caused by customization practices. A broader analysis of update-related CVEs from 2020 to 2024 reveals that over half originate from customization-induced issues. These findings highlight a critical yet underexamined reality: as customization increases, so does the attack surface, while current defenses fail to keep pace. We propose IMUP (Integrity-Centric Modular Update Platform), the first framework to address two key challenges: constructing a trustworthy cross-module integrity chain and scaling update performance under mass customization. IMUP combines three techniques: per-module chameleon hashing for integrity, server-side proof-of-work offloading to reduce device overhead, and server-side caching to reuse module combinations, minimizing rebuild costs. Security analysis shows that even when 95 percent of secret keys are exposed, forging a valid image incurs over 300 times the cost of the legitimate server. Experiments on heterogeneous IoT devices demonstrate that IMUP reduces server-side generation time by 2.9 times and device downtime by 5.9 times compared to a package-manager baseline.

cs.CR↗

arXiv2024

A Study on Prompt Injection Attack Against LLM-Integrated Mobile Robotic Systems

The integration of Large Language Models (LLMs) like GPT-4o into robotic systems represents a significant advancement in embodied artificial intelligence. These models can process multi-modal prompts, enabling them to generate more context-aware responses. However, this integration is not without challenges. One of the primary concerns is the potential security risks associated with using LLMs in robotic navigation tasks. These tasks require precise and reliable responses to ensure safe and effective operation. Multi-modal prompts, while enhancing the robot's understanding, also introduce complexities that can be exploited maliciously. For instance, adversarial inputs designed to mislead the model can lead to incorrect or dangerous navigational decisions. This study investigates the impact of prompt injections on mobile robot performance in LLM-integrated systems and explores secure prompt strategies to mitigate these risks. Our findings demonstrate a substantial overall improvement of approximately 30.8% in both attack detection and system performance with the implementation of robust defence mechanisms, highlighting their critical role in enhancing security and reliability in mission-oriented tasks.

cs.RO↗

arXiv2024

SafeEmbodAI: a Safety Framework for Mobile Robots in Embodied AI Systems

Embodied AI systems, including AI-powered robots that autonomously interact with the physical world, stand to be significantly advanced by Large Language Models (LLMs), which enable robots to better understand complex language commands and perform advanced tasks with enhanced comprehension and adaptability, highlighting their potential to improve embodied AI capabilities. However, this advancement also introduces safety challenges, particularly in robotic navigation tasks. Improper safety management can lead to failures in complex environments and make the system vulnerable to malicious command injections, resulting in unsafe behaviours such as detours or collisions. To address these issues, we propose \textit{SafeEmbodAI}, a safety framework for integrating mobile robots into embodied AI systems. \textit{SafeEmbodAI} incorporates secure prompting, state management, and safety validation mechanisms to secure and assist LLMs in reasoning through multi-modal data and validating responses. We designed a metric to evaluate mission-oriented exploration, and evaluations in simulated environments demonstrate that our framework effectively mitigates threats from malicious commands and improves performance in various environment settings, ensuring the safety of embodied AI systems. Notably, In complex environments with mixed obstacles, our method demonstrates a significant performance increase of 267\% compared to the baseline in attack scenarios, highlighting its robustness in challenging conditions.

cs.RO↗

arXiv2024

Expectations Versus Reality: Evaluating Intrusion Detection Systems in Practice

Our paper provides empirical comparisons between recent IDSs to provide an objective comparison between them to help users choose the most appropriate solution based on their requirements. Our results show that no one solution is the best, but is dependent on external variables such as the types of attacks, complexity, and network environment in the dataset. For example, BoT_IoT and Stratosphere IoT datasets both capture IoT-related attacks, but the deep neural network performed the best when tested using the BoT_IoT dataset while HELAD performed the best when tested using the Stratosphere IoT dataset. So although we found that a deep neural network solution had the highest average F1 scores on tested datasets, it is not always the best-performing one. We further discuss difficulties in using IDS from literature and project repositories, which complicated drawing definitive conclusions regarding IDS selection.

cs.CR↗

arXiv2021

Model-based Cybersecurity Analysis: Past Work and Future Directions

Model-based evaluation in cybersecurity has a long history. Attack Graphs (AGs) and Attack Trees (ATs) were the earlier developed graphical security models for cybersecurity analysis. However, they have limitations (e.g., scalability problem, state-space explosion problem, etc.) and lack the ability to capture other security features (e.g., countermeasures). To address the limitations and to cope with various security features, a graphical security model named attack countermeasure tree (ACT) was developed to perform security analysis by taking into account both attacks and countermeasures. In our research, we have developed different variants of a hierarchical graphical security model to solve the complexity, dynamicity, and scalability issues involved with security models in the security analysis of systems. In this paper, we summarize and classify security models into the following; graph-based, tree-based, and hybrid security models. We discuss the development of a hierarchical attack representation model (HARM) and different variants of the HARM, its applications, and usability in a variety of domains including the Internet of Things (IoT), Cloud, Software-Defined Networking, and Moving Target Defenses. We provide the classification of the security metrics, including their discussions. Finally, we highlight existing problems and suggest future research directions in the area of graphical security models and applications. As a result of this work, a decision-maker can understand which type of HARM will suit their network or security analysis requirements.

cs.CR↗

arXiv2020

Composite Metrics for Network Security Analysis

Security metrics present the security level of a system or a network in both qualitative and quantitative ways. In general, security metrics are used to assess the security level of a system and to achieve security goals. There are a lot of security metrics for security analysis, but there is no systematic classification of security metrics that are based on network reachability information. To address this, we propose a systematic classification of existing security metrics based on network reachability information. Mainly, we classify the security metrics into host-based and network-based metrics. The host-based metrics are classified into metrics ``without probability" and "with probability", while the network-based metrics are classified into "path-based" and "non-path based". Finally, we present and describe an approach to develop composite security metrics and it's calculations using a Hierarchical Attack Representation Model (HARM) via an example network. Our novel classification of security metrics provides a new methodology to assess the security of a system.

cs.CR↗

arXiv2019

CloudSafe: A Tool for an Automated Security Analysis for Cloud Computing

Cloud computing has been adopted widely, providing on-demand computing resources to improve perfornance and reduce the operational costs. However, these new functionalities also bring new ways to exploit the cloud computing environment. To assess the security of the cloud, graphical security models can be used, such as Attack Graphs and Attack Trees. However, existing models do not consider all types of threats, and also automating the security assessment functions are difficult. In this paper, we propose a new security assessment tool for the cloud named CloudSafe, an automated security assessment for the cloud. The CloudSafe tool collates various tools and frameworks to automate the security assessment process. To demonstrate the applicability of the CloudSafe, we conducted security assessment in Amazon AWS, where our experimental results showed that we can effectively gather security information of the cloud and carry out security assessment to produce security reports. Users and cloud service providers can use the security report generated by the CloudSafe to understand the security posture of the cloud being used/provided.

cs.CR↗