arXiv subjects

Kun Sun

Publications and source records attributed to Kun Sun.

At least 19 recordsLinked to original sources

arXiv2026

C-to-Rust Fallacy: Automatic Refactoring != Memory Security

Rust has emerged as the leading system programming language, offering strong memory and type safety guarantees without compromising performance. This positions it as a compelling alternative to traditional languages like C and C++, which are susceptible to memory security bugs. However, manually transforming C to Rust requires in-depth domain knowledge of the Rust language features, which requires significant effort for developers. To address this, tools for automatic C-to-Rust refactoring aim to generate safe Rust code leveraging static analysis and Large Language Models (LLMs). While these tools claim to achieve safety by reducing the unsafe Rust, the correlation with improving security is not clear. In this paper, we conduct a comprehensive empirical study on the reliability, safety, and correctness of various C-to-Rust refactoring methods. Specifically, we evaluate C2Rust-analyze, CROWN, C2SaferRust, and FLOURINE using a dataset of 116 C programs with memory security bugs from the NIST Juliet Test Suite. Based on 464 Rust programs generated by these tools, our evaluation focuses on three key aspects: the compilation correctness of the refactored programs, the effectiveness in mitigating original C bugs, and the tendency to introduce additional Rust bugs. The results indicate that 342 Rust programs fail to compile, 177 Rust programs inherit memory security bugs from the original C programs, and 77 new Rust bugs are introduced. We examine the rationale behind tool design and analyze the root cause of errors across various refactoring methods. Our findings indicate that current automated refactoring tools deliver memory safety as they define it, but not the broader memory security when adopting them.

cs.CR↗

arXiv2026

Overflip: Repetition-Induced Label Flips in Guardrail Models

Guardrail models are classifiers deployed to screen malicious prompts and responses in LLM-based services. To meet latency constraints, many lightweight guardrails adopt compact Transformer backbones (e.g., DeBERTa) that are trained with short context windows (typically 512 tokens) and rely on bucketed relative positional encodings to process longer inputs. Prior evaluations assume that a guardrail's decision is stable as the input is lengthened. We show that this assumption can fail. We identify Overflip, a repetition-induced instability where repeating a prompt causes the guardrail's prediction to flip (MAL$\to$BEN) as the sequence grows. We conduct experiments on 9 widely used lightweight guardrail models. Five exhibit MAL$\to$BEN flips on a benchmark of 100 prompts, with confidence margins shrinking steadily with repetition. Among these vulnerable models, flip rates range from 8% to 92%, with first flips occurring at roughly 2.6k--9.4k tokens. Our analysis suggests Overflip differs from traditional attention-dilution baselines, which aim to divert the model's attention away from tokens associated with malicious content, shifting it instead toward unrelated content, such as benign padding or shuffling. While Overflip preserves malicious content, it homogenizes token-level attention over repeated structure and induces a distinct, more gradual attention-dispersion trajectory than padding. Moreover, Overflip poses a greater threat to LLM services than traditional attention dilution methods. Because the bypassed prompt remains semantically intact and is still readily understood by downstream business LLMs, it can transmit malicious intent after passing the guardrail. These findings expose repetition as an attack surface for guardrail models and motivate length-robust evaluation and mitigation.

cs.AI↗

arXiv2026

More Granular, Less Trust: Enforcing Intra-Process Isolation with Arm CCA in an Untrusted Management Environment

With the increasing adoption of confidential computing, security-sensitive applications are often deployed in confidential virtual machines (CVMs), which reduce reliance on third-party cloud providers. However, privilege attacks originating from the OS remain a significant threat in these environments. Existing finer-grained isolation schemes, such as SHELTER, provide process-level protection but are still vulnerable to intraprocess attacks and potential collusion between the OS and intra-process adversaries. Many current intra-process isolation techniques continue to depend on the OS to manage and enforce isolation domains, leading to a large Trusted Computing Base (TCB). This gap highlights the need for more granular, less trust-dependent confidential computing solutions. In this paper, we present CCAegis, a system that extends the Arm Confidential Compute Architecture (CCA) to enforce intra-process isolation of sensitive data and operations, safeguarding them from both intraprocess adversaries and the OS. We employ static analysis to track the flow of sensitive data and identify functions that handle such data. Permission-switching instructions are inserted at the function call and return points, adjusting permissions via the Granule Protection Table (GPT) to ensure that only designated functions can access the isolated data. Notably, CCAegis places trust solely in the Secure Monitor, which configures the GPTs and manages domain switching, thereby minimizing the TCB. We implemented CCAegis on both an official emulator and a real development board to assess its performance. Our experimental results show that CCAegis effectively isolates sensitive data and operations, with performance overheads ranging from 1.01x to 1.43x compared to the original version across real-world cryptographic workloads.

cs.CR↗

arXiv2026

Temporal Risk on Satellites

Satellite vulnerabilities change over time as orbits shift, power margins tighten, and the space environment deteriorates. However, most cybersecurity risk frameworks still treat threats as static. In practice, the same exploit can be far more damaging during a critical maneuver than during routine operations. We propose a temporal risk assessment framework that makes time an explicit axis in satellite security analysis. It extends existing adversary behavior taxonomies with a five-dimensional temporal capability model and estimates exploitation difficulty across distinct temporal windows of a mission. Rather than producing a single risk score, the framework outputs a series of time-indexed likelihood-impact matrices. It discretizes missions into operationally meaningful time windows and environmental bands to show when systems are most exposed. This view helps operators avoid scheduling sensitive operations in high-risk periods and align defensive resources with a threat landscape that shifts over time.

cs.CR↗

arXiv2026

Contextual Semantic Relevance Tracks fMRI BOLD Responses During Naturalistic Speech Comprehension

Naturalistic language comprehension requires listeners to process both local probabilistic expectations and contextual semantic relations. This study tested whether contextual semantic relevance, measuring how strongly a target word relates to its recent semantic context, is associated with fMRI BOLD responses independently of word surprisal and lexical, timing, acoustic, and prosodic controls. We analyzed two public datasets: Alice (23 participants, one narrative) and Narratives (47 participants, 185 runs, four stories) using FIR/deconvolution and generalized additive mixed models. In Alice, semantic relevance was significant across all ROIs in FIR analyses, whereas surprisal was not. In GAMMs, both predictors showed broad significance. In Narratives, both predictors showed comparable spatial prevalence across ROIs. Semantic relevance showed robust BOLD associations across both datasets, with a particularly strong advantage over surprisal in the timing-sensitive Alice FIR analysis. The regionally heterogeneous direction of semantic relevance effects, with negative effects in posterior semantic regions and positive effects in frontal integration regions, suggests involvement of functionally distinct neural processes rather than a single uniform mechanism. These findings indicate that contextual semantic fit and local probabilistic expectation make partially distinct, dataset-dependent contributions to hemodynamic responses during naturalistic listening.

cs.CL↗

arXiv2026

Sequential Contextual Fit Predicts Human Behavioural and Neural Dynamics Across Domains

Human perception, action and decision making unfold in sequences, but computational predictors are often domain-specific. This study computes and tests sequential contextual fit (SCF), an embedding-based measure of how well a current information state matches its recent context. The metric uses a simple recency-weighted similarity kernel and can be applied to words, sounds, visual scenes, affective states, choices, actions and neural representations. Across language processing, music-evoked emotion, a subset of audiovisual emotion EEG data, gambling decisions, human activity recognition and decision-related EEG, lower contextual fit predicted longer processing times, larger affective or behavioural transitions and stronger neural-state changes. These effects remained after controlling for established predictors including surprisal, reinforcement-learning prediction error, acoustic change, visual change and sensor change. SCF therefore provides a computational measurement layer for relating contextual compatibility to behavioural processing and cognitive/neural state-transition dynamics.

cs.AI↗

arXiv2026

Contextual Semantic Relevance and Word Surprisal Predict N400 and P600 Dynamics During Naturalistic Reading

Word surprisal is a well-established computational predictor of human neural responses during language comprehension, but it remains less clear whether local semantic fit explains neural response variation beyond lexical expectation during naturalistic reading. Using the Dublin EEG-based Reading Experiment Corpus (DERCo), this study examined whether contextual semantic relevance predicts word-locked EEG activity in the N400 and P600 windows. Contextual semantic relevance was computed as an attention-aware measure of how strongly a target word is semantically connected to its recent discourse context, and it was compared with GPT-based word surprisal. Across 22 participants and 32 EEG channels, we tested both predictors using regression-based ERP analyses and generalized additive mixed models while controlling for lexical variables and repeated observations. Both predictors were reliably associated with EEG responses, but they showed partly different temporal and scalp-level patterns. Surprisal captured expectancy-related variation, whereas contextual semantic relevance showed robust effects across N400- and P600-window mean voltages, with particularly strong explanatory support in the P600 window. Model comparisons indicated that contextual semantic relevance contributed explanatory value beyond lexical controls and surprisal. These findings suggest that naturalistic reading depends on both lexical expectation and local semantic integration, and that contextual semantic relevance offers an interpretable computational link between discourse semantic fit and ERP dynamics.

cs.CL↗

arXiv2026

Mimic Human Cognition, Master Multi-Image Reasoning: A Meta-Action Framework for Enhanced Visual Understanding

While Multimodal Large Language Models (MLLMs) excel at single-image understanding, they exhibit significantly degraded performance in multi-image reasoning scenarios. Multi-image reasoning presents fundamental challenges including complex inter-relationships between images and scattered critical information across image sets. Inspired by human cognitive processes, we propose a Cognition-Inspired Meta-Action Framework (CINEMA), which decomposes multi-image reasoning into five structured meta-actions: Global, Focus, Hint, Think, and Answer, explicitly modeling the sequential cognitive steps humans naturally employ. For cold-start training, we introduce a Retrieval-Based Tree Sampling strategy that generates high-quality meta-action trajectories to bootstrap the model with reasoning patterns. During reinforcement learning, we adopt a two-stage paradigm: an exploration phase with Diversity-Preserving Strategy to avoid entropy collapse, followed by an annealed exploitation phase with DAPO to gradually strengthen exploitation. To train our model, we construct a dataset of 56k cold-start and 58k reinforcement learning instances spanning multi-image, multi-frame, and single-image tasks. We conduct extensive evaluations on multi-image reasoning benchmarks, video understanding benchmarks, and single-image benchmarks, achieving competitive state-of-the-art performance on several key benchmarks. Our model surpasses GPT-4o on the MUIR and MVMath benchmarks and notably outperforms specialized video reasoning models on video understanding benchmarks, demonstrating the effectiveness and generalizability of our human cognition-inspired reasoning framework.

cs.CV↗

arXiv2026

Prior over Evidence: Stereotype-Driven Diagnosis in LLM-Based L2 Pronunciation Feedback

Large language models are increasingly deployed for written pronunciation feedback in second-language (L2) English learning, under the assumption that their diagnoses are grounded in the supplied speech evidence rather than in priors from pretraining. This assumption is tested on 1,800 L2-Arctic utterances spanning six L1 backgrounds, three audio-capable LLMs, four pronunciation dimensions, and five evidence conditions ranging from a text-only baseline to numeric acoustic features and raw audio. Each (utterance x model x condition x dimension) cell is scored on three metrics: Rating Accuracy (RA) against gold labels, Evidence Coherence (EC) assessing internal consistency without ground truth, and Grounded Correctness (GC) evaluated against gold evidence. Results show three findings across models. First, rating accuracy and grounded reasoning decouple: 39.6% of judged cells contain internally coherent reasoning that supports a wrong rating, against only 15.8% where the reasoning supports a correct rating. Second, phoneme-level feedback converges to a fixed inventory of L2-English difficulty phones that recurs across all six L1 backgrounds and all evidence conditions. Third, acoustic evidence improves the rating only when the supplied feature directly probes the target dimension: textualised F0 range raises pitch-variation grounding from (0.18-0.19) to (0.45-0.62) across all three models, while stress and phoneme correctness, which require target-to-realisation alignment, remain ungrounded. The same audio waveform without textualised F0 values does not reproduce this improvement. These findings indicate that current general-purpose LLMs are more reliable as verbalisers of externally computed pronunciation evidence than as standalone diagnostic engines.

cs.CL↗

arXiv2026

UHR-Net: An Uncertainty-Aware Hypergraph Refinement Network for Medical Image Segmentation

Accurate lesion segmentation is crucial for clinical diagnosis and treatment planning. However, lesions often resemble surrounding tissues and exhibit ill-defined boundaries, leading to unstable predictions in boundary/transition regions. Moreover, small-lesion cues can be diluted by multi-scale feature extraction, causing under- or over-segmentation. To address these challenges, we propose an Uncertainty-Aware Hypergraph Refinement Network (UHR-Net). First, we introduce an Uncertainty-Oriented Instance Contrastive (UO-IC) pretraining strategy that couples geometry-aware copy-paste augmentation with hard-negative mining of lesion-like background regions to improve instance-level discrimination for small and visually ambiguous lesions. Second, we design an Uncertainty-Guided Hypergraph Refinement (UGHR) block, which derives an entropy-based uncertainty map from a coarse probability map to guide hypergraph refinement. By splitting hyperedge prototypes into foreground and background groups, UGHR decouples higher-order interactions and improves refinement in ambiguous regions. Experiments on five public benchmarks demonstrate consistent gains over strong baselines. Code is available at: https://github.com/CUGfreshman/UHR-Net.

cs.CV↗

arXiv2026

Prompt Overflow: What the Guardrail Inspects Is Not What the Model Infers

Guardrail models (a.k.a. safety checkers) are widely deployed to screen user inputs before they reach large language models (LLMs), serving as a primary defense against prompt injection attacks. Due to strict context constraints, these models handle overlength prompts through truncation or segmentation-based inspection. While prior work has focused on semantic adversarial inputs, the security implications of these long-input processing mechanisms remain largely unexplored. In this paper, we identify a critical blind spot arising from the mismatch between the limited inspection windows of guardrail models and the substantially larger context inference windows of downstream LLMs. We introduce a novel Prompt Overflow Attack, which exploits this mismatch by fragmenting malicious instructions and interleaving them with benign filler content across an overlong prompt, such that no individual inspected segment appears malicious while the full context remains actionable to the LLM. Through a systematic evaluation against state-of-the-art guardrail models, including Meta Llama Prompt Guard, IBM Granite Guardian, and DeBERTa-based detectors, we demonstrate that prompts reliably detected in short-context settings can evade guardrail models once adversarially manipulated into over-length inputs, yet remain fully actionable by downstream LLMs. We further propose potential defense strategies and outline mitigation directions to strengthen guardrail models.

cs.CR↗

arXiv2026

An Agentic System for Rare Disease Diagnosis with Traceable Reasoning

Rare diseases affect over 300 million individuals worldwide, yet timely and accurate diagnosis remains an urgent challenge. Patients often endure a prolonged diagnostic odyssey exceeding five years, marked by repeated referrals, misdiagnoses, and unnecessary interventions, leading to delayed treatment and substantial emotional and economic burdens. Here we present DeepRare, a multi-agent system for rare disease differential diagnosis decision support powered by large language models, integrating over 40 specialized tools and up-to-date knowledge sources. DeepRare processes heterogeneous clinical inputs, including free-text descriptions, structured Human Phenotype Ontology terms, and genetic testing results, to generate ranked diagnostic hypotheses with transparent reasoning linked to verifiable medical evidence. Evaluated across nine datasets from literature, case reports and clinical centres across Asia, North America and Europe spanning 14 medical specialties, DeepRare demonstrates exceptional performance on 3,134 diseases. In human-phenotype-ontology-based tasks, it achieves an average Recall@1 of 57.18%, outperforming the next-best method by 23.79%; in multi-modal tests, it reaches 69.1% compared with Exomiser's 55.9% on 168 cases. Expert review achieved 95.4% agreement on its reasoning chains, confirming their validity and traceability. Our work not only advances rare disease diagnosis but also demonstrates how the latest powerful large-language-model-driven agentic systems can reshape current clinical workflows.

cs.CL↗

arXiv2026

End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning

The integration of Large Language Models (LLMs) into healthcare is constrained by knowledge limitations, hallucinations, and a disconnect from Evidence-Based Medicine (EBM). While Retrieval-Augmented Generation (RAG) offers a solution, current systems often rely on static workflows that miss the iterative, hypothetico-deductive reasoning of clinicians. To address this, we introduce Deep-DxSearch, an agentic RAG system trained end-to-end via reinforcement learning (RL) for traceable diagnostic reasoning. Deep-DxSearch acts as an active investigator, treating the LLM as an agent within an environment of 16,000+ guideline-derived disease profiles, 150,000+ patient records for case-based reasoning, and over 27 million biomedical documents. Using soft verifiable rewards that co-optimize retrieval and reasoning, the model learns to formulate queries, evaluate evidence, and refine searches to close diagnostic gaps. Experiments show our end-to-end RL framework consistently outperforms prompt-engineering and training-free RAG methods. On in-distribution (ID) and out-of-distribution (OOD) benchmarks for common and rare diseases, Deep-DxSearch surpasses strong baselines-including GPT-4o, DeepSeek-R1, and medical-specific frameworks-achieving an average accuracy gain of 22.7% over the second-best model. In validation with 150 real-world cases, Deep-DxSearch boosts physicians' average diagnostic accuracy from 45.6% to 69.1%. These results indicate that evolving agentic systems to leverage statistical regularities in large-scale healthcare data is key for trustworthy diagnostic assistants. All data, code, and checkpoints are available at https://qiaoyu-zheng.github.io/Deep-DxSearch.

cs.CL↗

arXiv2026

Knowledge-enhanced Pretraining for Vision-language Pathology Foundation Model on Cancer Diagnosis

Vision-language foundation models have shown great promise in computational pathology but remain primarily data-driven, lacking explicit integration of medical knowledge. We introduce KEEP (KnowledgE-Enhanced Pathology), a foundation model that systematically incorporates disease knowledge into pretraining for cancer diagnosis. KEEP leverages a comprehensive disease knowledge graph encompassing 11,454 diseases and 139,143 attributes to reorganize millions of pathology image-text pairs into 143,000 semantically structured groups aligned with disease ontology hierarchies. This knowledge-enhanced pretraining aligns visual and textual representations within hierarchical semantic spaces, enabling deeper understanding of disease relationships and morphological patterns. Across 18 public benchmarks (over 14,000 whole-slide images) and 4 institutional rare cancer datasets (926 cases), KEEP consistently outperformed existing foundation models, showing substantial gains for rare subtypes. These results establish knowledge-enhanced vision-language modeling as a powerful paradigm for advancing computational pathology.

eess.IV↗

arXiv2025

Systematic Framework of Application Methods for Large Language Models in Language Sciences

Large Language Models (LLMs) are transforming language sciences. However, their widespread deployment currently suffers from methodological fragmentation and a lack of systematic soundness. This study proposes two comprehensive methodological frameworks designed to guide the strategic and responsible application of LLMs in language sciences. The first method-selection framework defines and systematizes three distinct, complementary approaches, each linked to a specific research goal: (1) prompt-based interaction with general-use models for exploratory analysis and hypothesis generation; (2) fine-tuning of open-source models for confirmatory, theory-driven investigation and high-quality data generation; and (3) extraction of contextualized embeddings for further quantitative analysis and probing of model internal mechanisms. We detail the technical implementation and inherent trade-offs of each method, supported by empirical case studies. Based on the method-selection framework, the second systematic framework proposed provides constructed configurations that guide the practical implementation of multi-stage research pipelines based on these approaches. We then conducted a series of empirical experiments to validate our proposed framework, employing retrospective analysis, prospective application, and an expert evaluation survey. By enforcing the strategic alignment of research questions with the appropriate LLM methodology, the frameworks enable a critical paradigm shift in language science research. We believe that this system is fundamental for ensuring reproducibility, facilitating the critical evaluation of LLM mechanisms, and providing the structure necessary to move traditional linguistics from ad-hoc utility to verifiable, robust science.

cs.CL↗

arXiv2025

When Code Crosses Borders: A Security-Centric Study of LLM-based Code Translation

Code translation is crucial for cross-language codebase migration, and large language models (LLMs) have emerged as a promising technique to automate this process. However, the security implications of using LLMs for code translation remain largely unexplored, as existing evaluations primarily focus on syntactic and functional correctness. To bridge this gap, we conduct a security-centric empirical study to investigate the risks of vulnerabilities being introduced or preserved during LLM-based translation. Our study involves a rigorous evaluation of five state-of-the-art LLMs on a curated dataset of 720 security-related code samples across four programming languages (Java, PHP, C, C++) and nine Common Weakness Enumeration (CWE) categories. The results reveal significant security degradation, with 28.6\% to 45\% of translations introducing new vulnerabilities. Web-related flaws, particularly in input validation, proved most challenging for LLMs. Furthermore, we identify and categorize the root causes of these vulnerable translations into a taxonomy of five major error types. Based on our findings, we develop and evaluate a Retrieval-Augmented Generation (RAG)-based mitigation strategy, which successfully reduces the vulnerability introduction rate by 32.8\%. Our study provides the first large-scale evidence of serious security risks in LLM-based code translation and demonstrates the potential of knowledge-enhanced prompting to mitigate them.

cs.CR↗

arXiv2025

When Genes Speak: A Semantic-Guided Framework for Spatially Resolved Transcriptomics Data Clustering

Spatial transcriptomics enables gene expression profiling with spatial context, offering unprecedented insights into the tissue microenvironment. However, most computational models treat genes as isolated numerical features, ignoring the rich biological semantics encoded in their symbols. This prevents a truly deep understanding of critical biological characteristics. To overcome this limitation, we present SemST, a semantic-guided deep learning framework for spatial transcriptomics data clustering. SemST leverages Large Language Models (LLMs) to enable genes to "speak" through their symbolic meanings, transforming gene sets within each tissue spot into biologically informed embeddings. These embeddings are then fused with the spatial neighborhood relationships captured by Graph Neural Networks (GNNs), achieving a coherent integration of biological function and spatial structure. We further introduce the Fine-grained Semantic Modulation (FSM) module to optimally exploit these biological priors. The FSM module learns spot-specific affine transformations that empower the semantic embeddings to perform an element-wise calibration of the spatial features, thus dynamically injecting high-order biological knowledge into the spatial context. Extensive experiments on public spatial transcriptomics datasets show that SemST achieves state-of-the-art clustering performance. Crucially, the FSM module exhibits plug-and-play versatility, consistently improving the performance when integrated into other baseline methods.

cs.LG↗

arXiv2025

NeuroDeX: Unlocking Diverse Support in Decompiling Deep Neural Network Executables

On-device deep learning models have extensive real world demands. Deep learning compilers efficiently compile models into executables for deployment on edge devices, but these executables may face the threat of reverse engineering. Previous studies have attempted to decompile DNN executables, but they face challenges in handling compilation optimizations and analyzing quantized compiled models. In this paper, we present NeuroDeX to unlock diverse support in decompiling DNN executables. NeuroDeX leverages the semantic understanding capabilities of LLMs along with dynamic analysis to accurately and efficiently perform operator type recognition, operator attribute recovery and model reconstruction. NeuroDeX can recover DNN executables into high-level models towards compilation optimizations, different architectures and quantized compiled models. We conduct experiments on 96 DNN executables across 12 common DNN models. Extensive experimental results demonstrate that NeuroDeX can decompile non-quantized executables into nearly identical high-level models. NeuroDeX can recover functionally similar high-level models for quantized executables, achieving an average top-1 accuracy of 72%. NeuroDeX offers a more comprehensive and effective solution compared to previous DNN executables decompilers.

cs.LG↗