arXiv subjects

Jun Sun

Publications and source records attributed to Jun Sun.

At least 109 records · Page 6Linked to original sources

arXiv2025

AutoGraph: A Knowledge-Graph Framework for Modeling Interface Interaction and Automating Procedure Execution in Digital Nuclear Control Rooms

Digitalization in nuclear power plant (NPP) control rooms is reshaping how operators interact with procedures and interface elements. However, existing computer-based procedures (CBPs) often lack semantic integration with human-system interfaces (HSIs), limiting their capacity to support intelligent automation and increasing the risk of human error, particularly under dynamic or complex operating conditions. In this study, we present AutoGraph, a knowledge-graph-based framework designed to formalize and automate procedure execution in digitalized NPP environments.AutoGraph integrates (1) a proposed HTRPM tracking module to capture operator interactions and interface element locations; (2) an Interface Element Knowledge Graph (IE-KG) encoding spatial, semantic, and structural properties of HSIs; (3) automatic mapping from textual procedures to executable interface paths; and (4) an execution engine that maps textual procedures to executable interface paths. This enables the identification of cognitively demanding multi-action steps and supports fully automated execution with minimal operator input. We validate the framework through representative control room scenarios, demonstrating significant reductions in task completion time and the potential to support real-time human reliability assessment. Further integration into dynamic HRA frameworks (e.g., COGMIF) and real-time decision support systems (e.g., DRIF) illustrates AutoGraph extensibility in enhancing procedural safety and cognitive performance in complex socio-technical systems.

cs.HC↗

arXiv2025

LLMScan: Causal Scan for LLM Misbehavior Detection

Despite the success of Large Language Models (LLMs) across various fields, their potential to generate untruthful, biased and harmful responses poses significant risks, particularly in critical applications. This highlights the urgent need for systematic methods to detect and prevent such misbehavior. While existing approaches target specific issues such as harmful responses, this work introduces LLMScan, an innovative LLM monitoring technique based on causality analysis, offering a comprehensive solution. LLMScan systematically monitors the inner workings of an LLM through the lens of causal inference, operating on the premise that the LLM's `brain' behaves differently when misbehaving. By analyzing the causal contributions of the LLM's input tokens and transformer layers, LLMScan effectively detects misbehavior. Extensive experiments across various tasks and models reveal clear distinctions in the causal distributions between normal behavior and misbehavior, enabling the development of accurate, lightweight detectors for a variety of misbehavior detection tasks.

cs.AI↗

arXiv2025

On-Demand Scenario Generation for Testing Automated Driving Systems

The safety and reliability of Automated Driving Systems (ADS) are paramount, necessitating rigorous testing methodologies to uncover potential failures before deployment. Traditional testing approaches often prioritize either natural scenario sampling or safety-critical scenario generation, resulting in overly simplistic or unrealistic hazardous tests. In practice, the demand for natural scenarios (e.g., when evaluating the ADS's reliability in real-world conditions), critical scenarios (e.g., when evaluating safety in critical situations), or somewhere in between (e.g., when testing the ADS in regions with less civilized drivers) varies depending on the testing objectives. To address this issue, we propose the On-demand Scenario Generation (OSG) Framework, which generates diverse scenarios with varying risk levels. Achieving the goal of OSG is challenging due to the complexity of quantifying the criticalness and naturalness stemming from intricate vehicle-environment interactions, as well as the need to maintain scenario diversity across various risk levels. OSG learns from real-world traffic datasets and employs a Risk Intensity Regulator to quantitatively control the risk level. It also leverages an improved heuristic search method to ensure scenario diversity. We evaluate OSG on the Carla simulators using various ADSs. We verify OSG's ability to generate scenarios with different risk levels and demonstrate its necessity by comparing accident types across risk levels. With the help of OSG, we are now able to systematically and objectively compare the performance of different ADSs based on different risk levels.

cs.RO↗

arXiv2025

BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models

Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks: carefully crafted triggers in the input can manipulate the model to produce adversary-specified outputs. While prior research has predominantly focused on backdoor risks in vision and classification settings, the vulnerability of LLMs in open-ended text generation remains underexplored. To fill this gap, we introduce BackdoorLLM (Our BackdoorLLM benchmark was awarded First Prize in the SafetyBench competition, https://www.mlsafety.org/safebench/winners, organized by the Center for AI Safety, https://safe.ai/.), the first comprehensive benchmark for systematically evaluating backdoor threats in text-generation LLMs. BackdoorLLM provides: (i) a unified repository of benchmarks with a standardized training and evaluation pipeline; (ii) a diverse suite of attack modalities, including data poisoning, weight poisoning, hidden-state manipulation, and chain-of-thought hijacking; (iii) over 200 experiments spanning 8 distinct attack strategies, 7 real-world scenarios, and 6 model architectures; (iv) key insights into the factors that govern backdoor effectiveness and failure modes in LLMs; and (v) a defense toolkit encompassing 7 representative mitigation techniques. Our code and datasets are available at https://github.com/bboylyg/BackdoorLLM. We will continuously incorporate emerging attack and defense methodologies to support the research in advancing the safety and reliability of LLMs.

cs.AI↗

arXiv2025

Analog Self-Interference Cancellation in Full-Duplex Radios: A Fundamental Limit Perspective

Analog self-interference cancellation (A-SIC) plays a crucial role in the implementation of in-band full-duplex (IBFD) radios, due to the fact that the inherent transmit (Tx) noise can only be addressed in the analog domain. It is thus natural to ask what the performance limit of A-SIC is in practical systems, which is still quite underexplored so far. In this paper, we aim to close this gap by characterizing the fundamental performance of A-SIC which employs the common multi-tap delay (MTD) architecture, by accounting for the following practical issues: 1) Nonstationarity of the Tx signal; 2) Nonlinear distortions on the Tx signal; 3) Multipath channel corresponding to the self-interference (SI); 4) Maximum amplitude constraint on the MTD tap weights. Our findings include: 1) The average approximation error for the cyclostationary Tx signals is equal to that for the stationary white Gaussian process, thus greatly simplifying the performance analysis and the optimization procedure. 2) The approximation error for the multipath SI channel can be decomposed as the sum of the approximation error for the single-path scenario. By leveraging these structural results, the optimization framework and algorithms which characterize the fundamental limit of A-SIC, by taking into account all the aforementioned practical factors, are provided.

eess.SP↗

arXiv2025

Conformance Testing of Relational DBMS Against SQL Specifications

A Relational Database Management System (RDBMS) is one of the fundamental software that supports a wide range of applications, making it critical to identify bugs within these systems. There has been active research on testing RDBMS, most of which employ crash or use metamorphic relations as the oracle. Although existing approaches can detect bugs in RDBMS, they are far from comprehensively evaluating the RDBMS's correctness (i.e., with respect to the semantics of SQL). In this work, we propose a method to test the semantic conformance of RDBMS i.e., whether its behavior respects the intended semantics of SQL. Specifically, we have formally defined the semantics of SQL and implemented them in Prolog. Then, the Prolog implementation serves as the reference RDBMS, enabling differential testing on existing RDBMS. We applied our approach to four widely-used and thoroughly tested RDBMSs, i.e., MySQL, TiDB, SQLite, and DuckDB. In total, our approach uncovered 19 bugs and 11 inconsistencies, which are all related to violating the SQL specification or missing/unclear specification, thereby demonstrating the effectiveness and applicability of our approach.

cs.DB↗

arXiv2025

Copper delocalization leads to ultralow thermal conductivity in chalcohalide CuBiSeCl2

Mixed anion halide-chalcogenide materials have attracted considerable attention due to their exceptional optoelectronic properties, making them promising candidates for various applications. Among these, CuBiSeCl_2 has recently been experimentally identified with remarkably low lattice thermal conductivity (k_L). In this study, we employ Wigner transport theory combined with neuroevolution machine learning potential (NEP)-assisted self-consistent phonon calculations to unravel the microscopic origins of this low k_L. Our findings reveal that the delocalization and weak bonding of copper atoms are key contributors to the strong phonon anharmonicity and wavelike tunneling (random walk diffusons). These insights deepen our understanding of the relationship between bonding characteristics, anharmonicity, delocalization, and vibrational dynamics, paving the way for the design and optimization of CuBiSeCl_2 and analogous materials for advanced phonon engineering applications.

cond-mat.mtrl-sci↗

arXiv2025

ai.txt: A Domain-Specific Language for Guiding AI Interactions with the Internet

We introduce ai.txt, a novel domain-specific language (DSL) designed to explicitly regulate interactions between AI models, agents, and web content, addressing critical limitations of the widely adopted robots.txt standard. As AI increasingly engages with online materials for tasks such as training, summarization, and content modification, existing regulatory methods lack the necessary granularity and semantic expressiveness to ensure ethical and legal compliance. ai.txt extends traditional URL-based access controls by enabling precise element-level regulations and incorporating natural language instructions interpretable by AI systems. To facilitate practical deployment, we provide an integrated development environment with code autocompletion and automatic XML generation. Furthermore, we propose two compliance mechanisms: XML-based programmatic enforcement and natural language prompt integration, and demonstrate their effectiveness through preliminary experiments and case studies. Our approach aims to aid the governance of AI-Internet interactions, promoting responsible AI use in digital ecosystems.

cs.NI↗

arXiv2025

A Test Suite for Efficient Robustness Evaluation of Face Recognition Systems

Face recognition is a widely used authentication technology in practice, where robustness is required. It is thus essential to have an efficient and easy-to-use method for evaluating the robustness of (possibly third-party) trained face recognition systems. Existing approaches to evaluating the robustness of face recognition systems are either based on empirical evaluation (e.g., measuring attacking success rate using state-of-the-art attacking methods) or formal analysis (e.g., measuring the Lipschitz constant). While the former demands significant user efforts and expertise, the latter is extremely time-consuming. In pursuit of a comprehensive, efficient, easy-to-use and scalable estimation of the robustness of face recognition systems, we take an old-school alternative approach and introduce RobFace, i.e., evaluation using an optimised test suite. It contains transferable adversarial face images that are designed to comprehensively evaluate a face recognition system's robustness along a variety of dimensions. RobFace is system-agnostic and still consistent with system-specific empirical evaluation or formal analysis. We support this claim through extensive experimental results with various perturbations on multiple face recognition systems. To our knowledge, RobFace is the first system-agnostic robustness estimation test suite.

cs.SE↗

arXiv2025

Type II Singularities of Lagrangian Mean Curvature Flow with Zero Maslov Class

In this paper, we will prove some rigidity theorems for blow up limits to Type II singularities of Lagrangian mean curvature flow with zero Maslov class or almost calibrated Lagrangian mean curvature flows, especially for Lagrangian translating solitons in any dimension. These theorems generalized previous corresponding results from two dimensional case to arbitrarily dimensional case.

math.DG↗

arXiv2025

Foliation of constant harmonic mean curvature surfaces in asymptotic Schwarzschild spaces

This paper investigates the volume-preserving harmonic mean curvature flow in asymptotically Schwarzschild spaces. We demonstrate the long-time existence and exponential convergence of this flow with a coordinate sphere of large radius serving as the initial surface in the asymptotically flat end, which eventually converges to a constant harmonic mean curvature surface. We also establish that these surfaces form a foliation of the space outside a large ball. Finally, we utilize this foliation to define the center of mass, proving that it agrees with the center of mass defined by the ADM formulation of the initial data set.

math.DG↗

arXiv2025

PINK: physical-informed machine learning for lattice thermal conductivity

Lattice thermal conductivity ($κ_L$) is crucial for efficient thermal management in electronics and energy conversion technologies. Traditional methods for predicting \k{appa}L are often computationally expensive, limiting their scalability for large-scale material screening. Empirical models, such as the Slack model, offer faster alternatives but require time-consuming calculations for key parameters such as sound velocity and the Gruneisen parameter. This work presents a high-throughput framework, physical-informed kappa (PINK), which combines the predictive power of crystal graph convolutional neural networks (CGCNNs) with the physical interpretability of the Slack model to predict \k{appa}L directly from crystallographic information files (CIFs). Unlike previous approaches, PINK enables rapid, batch predictions by extracting material properties such as bulk and shear modulus from CIFs using a well-trained CGCNN model. These properties are then used to compute the necessary parameters for $κ_L$ calculation through a simplified physical formula. PINK was applied to a dataset of 377,221 stable materials, enabling the efficient identification of promising candidates with ultralow $κ_L$ values, such as Ag$_3$Te$_4$W and Ag$_3$Te$_4$Ta. The platform, accessible via a user-friendly interface, offers an unprecedented combination of speed, accuracy, and scalability, significantly accelerating material discovery for thermal management and energy conversion applications.

cond-mat.mtrl-sci↗

arXiv2025

PALo: Learning Posture-Aware Locomotion for Quadruped Robots

With the rapid development of embodied intelligence, locomotion control of quadruped robots on complex terrains has become a research hotspot. Unlike traditional locomotion control approaches focusing solely on velocity tracking, we pursue to balance the agility and robustness of quadruped robots on diverse and complex terrains. To this end, we propose an end-to-end deep reinforcement learning framework for posture-aware locomotion named PALo, which manages to handle simultaneous linear and angular velocity tracking and real-time adjustments of body height, pitch, and roll angles. In PALo, the locomotion control problem is formulated as a partially observable Markov decision process, and an asymmetric actor-critic architecture is adopted to overcome the sim-to-real challenge. Further, by incorporating customized training curricula, PALo achieves agile posture-aware locomotion control in simulated environments and successfully transfers to real-world settings without fine-tuning, allowing real-time control of the quadruped robot's locomotion and body posture across challenging terrains. Through in-depth experimental analysis, we identify the key components of PALo that contribute to its performance, further validating the effectiveness of the proposed method. The results of this study provide new possibilities for the low-level locomotion control of quadruped robots in higher dimensional command spaces and lay the foundation for future research on upper-level modules for embodied intelligence.

cs.RO↗

arXiv2025

Detecting Essence Code Clones via Information Theoretic Analysis

Code cloning, a widespread practice in software development, involves replicating code fragments to save time but often at the expense of software maintainability and quality. In this paper, we address the specific challenge of detecting "essence clones", a complex subtype of Type-3 clones characterized by sharing critical logic despite different peripheral codes. Traditional techniques often fail to detect essence clones due to their syntactic focus. To overcome this limitation, we introduce ECScan, a novel detection tool that leverages information theory to assess the semantic importance of code lines. By assigning weights to each line based on its information content, ECScan emphasizes core logic over peripheral code differences. Our comprehensive evaluation across various real-world projects shows that ECScan significantly outperforms existing tools in detecting essence clones, achieving an average F1-score of 85%. It demonstrates robust performance across all clone types and offers exceptional scalability. This study advances clone detection by providing a practical tool for developers to enhance code quality and reduce maintenance burdens, emphasizing the semantic aspects of code through an innovative information-theoretic approach.

cs.SE↗

arXiv2025

Zero-Shot Defense Against Toxic Images via Inherent Multimodal Alignment in LVLMs

Large Vision-Language Models (LVLMs) have made significant strides in multimodal comprehension, thanks to extensive pre-training and fine-tuning on large-scale visual datasets. However, despite their robust textual safety mechanisms, they remain vulnerable to harmful visual inputs. Existing safeguards-typically relying on pre-filtering or fine-tuning-incur high costs and diminish overall utility. To address this critical vulnerability, we introduce SafeCLIP, a lightweight method that leverages LVLMs inherent multimodal alignment for zero-shot toxic image detection. By projecting CLIPs discarded CLS token into its text space and matching it with toxic descriptors, SafeCLIP detects harmful content without any architectural changes-adding minimal latency and enabling dynamic safety corrections during inference and fine-tuning.Experiments show that SafeCLIP achieves a 66.9% defense success rate with only 3.2% false positive rate and 7.2% overhead. In contrast, state-of-the-art methods achieve 52.9% success but have a 10.7% false positive rate and 210% overhead. Our work demonstrates that leveraging inherent multimodal alignment can yield efficient, low-cost LVLM safety. Code is available at anonymous.4open.science/r/safeclip-2C01.

cs.CL↗

arXiv2025

Verification of Bit-Flip Attacks against Quantized Neural Networks

In the rapidly evolving landscape of neural network security, the resilience of neural networks against bit-flip attacks (i.e., an attacker maliciously flips an extremely small amount of bits within its parameter storage memory system to induce harmful behavior), has emerged as a relevant area of research. Existing studies suggest that quantization may serve as a viable defense against such attacks. Recognizing the documented susceptibility of real-valued neural networks to such attacks and the comparative robustness of quantized neural networks (QNNs), in this work, we introduce BFAVerifier, the first verification framework designed to formally verify the absence of bit-flip attacks or to identify all vulnerable parameters in a sound and rigorous manner. BFAVerifier comprises two integral components: an abstraction-based method and an MILP-based method. Specifically, we first conduct a reachability analysis with respect to symbolic parameters that represent the potential bit-flip attacks, based on a novel abstract domain with a sound guarantee. If the reachability analysis fails to prove the resilience of such attacks, then we encode this verification problem into an equivalent MILP problem which can be solved by off-the-shelf solvers. Therefore, BFAVerifier is sound, complete, and reasonably efficient. We conduct extensive experiments, which demonstrate its effectiveness and efficiency across various network architectures, quantization bit-widths, and adversary capabilities.

cs.CR↗

arXiv2025

Space of ancient caloric functions on some manifolds beyond volume doubling

Under a condition that breaks the volume doubling barrier, we obtain a time polynomial structure result on the space of ancient caloric functions with polynomial growth on manifolds. As a byproduct, it is shown that the finiteness result for the space of harmonic functions with polynomial growth on manifolds in \cite{CM97} and \cite{Li97} are essentially sharp, except for the multi-end cases, addressing an issue raised in \cite{CM98} and removing all {\it local} topological or geometric conditions on the manifold with respect to a reference point.

math.DG↗

arXiv2025

Translating Solitons to a Lagrangian mean curvature flow with zero Maslov class

It is known that there is no a Type I singularity for the Lagrangian mean curvature flow with zero Maslov class. In this paper, we study translating solitons which are important models of Type II singularities. A necessary condition for a blow-up limit arising at a Type II singularity of a Lagrangian mean curvature flow with zero Maslov class is provided. As an application, we try to understand the important open question proposed by Joyce-Lee-Tsui and Neves-Tian, whether the Lagrangian translating solitons constructed by Joyce-Lee-Tsui can be a blow-up limit for a Lagrangian mean curvature flow with zero Maslov class.

math.DG↗