arXiv subjects

Ting Zhang

Publications and source records attributed to Ting Zhang.

At least 55 records · Page 3Linked to original sources

arXiv2026

"Your AI, My Shell": Demystifying Prompt Injection Attacks on Agentic AI Coding Editors

Agentic AI coding editors driven by large language models have recently become more popular due to their ability to improve developer productivity during software development. Modern editors such as Cursor are designed not just for code completion, but also with more system privileges for complex coding tasks (e.g., run commands in the terminal, access development environments, and interact with external systems). While this brings us closer to the "fully automated programming" dream, it also raises new security concerns. In this study, we present the first empirical analysis of prompt injection attacks targeting these high-privilege agentic AI coding editors. We show how attackers can remotely exploit these systems by poisoning external development resources with malicious instructions, effectively hijacking AI agents to run malicious commands, turning "your AI" into "attacker's shell". To perform this analysis, we implement AIShellJack, an automated testing framework for assessing prompt injection vulnerabilities in agentic AI coding editors. AIShellJack contains 314 unique attack payloads that cover 70 techniques from the MITRE ATT&CK framework. Using AIShellJack, we conduct a large-scale evaluation on GitHub Copilot and Cursor, and our evaluation results show that attack success rates can reach as high as 84% for executing malicious commands. Moreover, these attacks are proven effective across a wide range of objectives, ranging from initial access and system discovery to credential theft and data exfiltration.

cs.CR↗

arXiv2026

SMART: Self-Generating and Self-Validating Multi-Dimensional Assessment for LLMs' Mathematical Problem Solving

Large Language Models (LLMs) have achieved remarkable performance across a wide range of mathematical benchmarks. However, concerns remain as to whether these successes reflect genuine reasoning or superficial pattern recognition. Existing evaluation methods, which typically focus either on the final answer or on the intermediate reasoning steps, reduce mathematical reasoning to a shallow input-output mapping, overlooking its inherently multi-stage and multi-dimensional cognitive nature. Inspired by Polya's problem-solving theory, we propose SMART, a benchmark that decomposes mathematical problem-solving into four cognitive dimensions: Semantic Understanding, Mathematical Reasoning, Arithmetic Computation, and Reflection & Refinement, and introduces dimension-specific tasks to measure the corresponding cognitive processes of LLMs. We apply SMART to 22 state-of-the-art open- and closed-source LLMs and uncover substantial discrepancies in their capabilities across dimensions. Our findings reveal genuine weaknesses in current models and motivate a new metric, the All-Pass Score, designed to better capture true problem-solving capability.

cs.AI↗

arXiv2026

A Review of Variational Quantum Algorithms: Insights into Fault-Tolerant Quantum Computing

Variational quantum algorithms (VQAs) have established themselves as a central computational paradigm in the Noisy Intermediate-Scale Quantum (NISQ) era. By coupling parameterized quantum circuits (PQCs) with classical optimization, they operate effectively under strict hardware limitations. However, as quantum architectures transition toward early fault-tolerant (EFT) and ultimate fault-tolerant (FT) regimes, the foundational principles and long-term viability of VQAs require systematic reassessment. This review offers an insightful analysis of VQAs and their progression toward the fault-tolerant regime. We deconstruct the core algorithmic framework by examining ansatz design and classical optimization strategies, including cost function formulation, gradient computation, and optimizer selection. Concurrently, we evaluate critical training bottlenecks, notably barren plateaus (BPs), alongside established mitigation strategies. The discussion then explores the EFT phase, detailing how the integration of quantum error mitigation and partial error correction can sustain algorithmic performance. Addressing the FT phase, we analyze the inherent challenges confronting current hybrid VQA models. Furthermore, we synthesize recent VQA applications across diverse domains, including many-body physics, quantum chemistry, machine learning, and mathematical optimization. Ultimately, this review outlines a theoretical roadmap for adapting quantum algorithms to future hardware generations, elucidating how variational principles can be systematically refined to maintain their relevance and efficiency within an error-corrected computational environment.

quant-ph↗

arXiv2026

Local decay estimates for the bi-Laplacian Nonautonomous Schrödinger equation

In this paper, we establish local decay estimates for the bi-Laplacian Schrödinger equation with time-dependent (in particular, quasi-periodic) potentials in spatial dimension $n\ge14$. Moreover, under stronger spectral regularity hypotheses, the same result can be extended to dimension $n\ge9$. Our approach, based on asymptotic completeness and the existence of the channel wave operator, departs from standard resolvent-based methods. In addition, global-in-time Strichartz estimates are derived from the local decay estimates.

math.AP↗

arXiv2026

Semantics-Aligned, Curriculum-Driven, and Reasoning-Enhanced Vulnerability Repair Framework

Current learning-based Automated Vulnerability Repair (AVR) approaches, while promising, often fail to generalize effectively in real-world scenarios. Our diagnostic analysis reveals three fundamental weaknesses in state-of-the-art AVR approaches: (1) limited cross-repository generalization, with performance drops on unseen codebases; (2) inability to capture long-range dependencies, causing a performance degradation on complex, multi-hunk repairs; and (3) over-reliance on superficial lexical patterns, leading to significant performance drops on vulnerabilities with minor syntactic variations like variable renaming. To address these limitations, we propose SeCuRepair, a semantics-aligned, curriculum-driven, and reasoning-enhanced framework for vulnerability repair. At its core, SeCuRepair adopts a reason-then-edit paradigm, requiring the model to articulate why and how a vulnerability should be fixed before generating the patch. This explicit reasoning enforces a genuine understanding of repair logic rather than superficial memorization of lexical patterns. SeCuRepair also moves beyond traditional supervised fine-tuning and employs semantics-aware reinforcement learning, rewarding patches for their syntactic and semantic alignment with the oracle patch rather than mere token overlap. Complementing this, a difficulty-aware curriculum progressively trains the model, starting with simple fixes and advancing to complex, multi-hunk coordinated edits. We evaluate SeCuRepair on strict, repository-level splits of BigVul and newly crafted PrimeVul_AVR datasets. SeCuRepair significantly outperforms all baselines, surpassing the best-performing baselines by 34.52% on BigVul and 31.52% on PrimeVul\textsubscript{AVR} in terms of CodeBLEU, respectively. Comprehensive ablation studies further confirm that each component of our framework contributes to its final performance.

cs.SE↗

arXiv2026

Revisiting Vulnerability Patch Identification on Data in the Wild

Attacks can exploit zero-day or one-day vulnerabilities that are not publicly disclosed. To detect these vulnerabilities, security researchers monitor development activities in open-source repositories to identify unreported security patches. The sheer volume of commits makes this task infeasible to accomplish manually. Consequently, security patch detectors commonly trained and evaluated on security patches linked from vulnerability reports in the National Vulnerability Database (NVD). In this study, we assess the effectiveness of these detectors when applied in-the-wild. Our results show that models trained on NVD-derived data show substantially decreased performance, with decreases in F1-score of up to 90\% when tested on in-the-wild security patches, rendering them impractical for real-world use. An analysis comparing security patches identified in-the-wild and commits linked from NVD reveals that they can be easily distinguished from each other. Security patches associated with NVD have different distribution of commit messages, vulnerability types, and composition of changes. These differences suggest that NVD may be unsuitable as the \textit{sole} source of data for training models to detect security patches. We find that constructing a dataset that combines security patches from NVD data with a small subset of manually identified security patches can improve model robustness.

cs.SE↗

arXiv2026

VisioMath: Benchmarking Figure-based Mathematical Reasoning in LMMs

Large Multimodal Models have achieved remarkable progress in integrating vision and language, enabling strong performance across perception, reasoning, and domain-specific tasks. However, their capacity to reason over multiple, visually similar inputs remains insufficiently explored. Such fine-grained comparative reasoning is central to real-world tasks, especially in mathematics and education, where learners must often distinguish between nearly identical diagrams to identify correct solutions. To address this gap, we present VisioMath, a curated benchmark of 1,800 high-quality K-12 mathematics problems in which all candidate answers are diagrams with subtle visual similarities. A comprehensive evaluation of state-of-the-art LMMs, covering both leading closed-source systems and widely adopted open-source models, reveals a consistent decline in accuracy as inter-image similarity increases. Analysis indicates that the dominant failure mode stems from image-text misalignment: rather than grounding reasoning in textual cues, models often resort to shallow positional heuristics, resulting in systematic errors. We further explore three alignment-oriented strategies, spanning training-free approaches and finetuning, and achieve substantial accuracy gains. We hope that VisioMath will serve as a rigorous benchmark and catalyst for developing LMMs toward deeper diagram understanding, precise comparative reasoning, and grounded multi-image-text integration.

cs.AI↗

arXiv2026

Cross-sphere Coupling and Source Inversion of Ionospheric Disturbances Associated with the 2025 Myanmar Strike-slip Earthquake from BeiDou GEO and Multi-GNSS Observations

Focusing on the M7.9 earthquake in Myanmar in 2025, this study comprehensively utilizes data from BeiDou geostationary satellites of the Chinese Continental Crustal Movement Observation Network and multi-system Global Navigation Satellite Systems (GNSS). The spatiotemporal evolution characteristics and physical mechanisms of pre-seismic ionospheric anomalies and co-seismic ionospheric disturbances were systematically analyzed. By employing the moving interquartile range method combined with solar-terrestrial environmental parameters, a negative Total Electron Content (TEC) anomaly associated with the seismogenic region was identified three days before the earthquake. The equatorial conjugate structure of this TEC anomaly revealed a multi-path coupling effect between the lithosphere, atmosphere, and ionosphere. The extraction of Coherent Ionospheric Disturbance (CID) signals based on wavelet transform and band-pass filtering indicated that the co-seismic ionospheric disturbances were dominated by acoustic-gravity waves in the 2-8 mHz frequency band, propagating at a speed of approximately 1.2 km/s, and exhibiting an asymmetric pattern in the southeast direction. A spatial density-weighted method for locating the source of ionospheric disturbances was proposed, elucidating the joint control mechanism of fault strike-slip motion, geomagnetic field modulation, and equatorial electrojet on the disturbance energy. The results confirm that the high spatiotemporal resolution of BeiDou GEO satellites and multi-system GNSS significantly enhances the capability to capture weak ionospheric anomaly signals associated with earthquakes. These results provide additional observational constraints on space-based Lithosphere-Atmosphere-Ionosphere Coupling (LAIC) processes and may contribute to the development of ionosphere-based earthquake monitoring techniques.

physics.geo-ph↗

arXiv2026

Beyond Function-Level Analysis: Context-Aware Reasoning for Inter-Procedural Vulnerability Detection

Recent progress in ML and LLMs has improved vulnerability detection, and recent datasets have reduced label noise and unrelated code changes. However, most existing approaches still operate at the function level, where models are asked to predict whether a single function is vulnerable without inter-procedural context. In practice, vulnerability presence and root cause often depend on contextual information. Naively appending such context is not a reliable solution: real-world context is long, redundant, and noisy, and we find that unstructured context frequently degrades the performance of strong fine-tuned code models. We present CPRVul, a context-aware vulnerability detection framework that couples Context Profiling and Selection with Structured Reasoning. CPRVul constructs a code property graph, and extracts candidate context. It then uses an LLM to generate security-focused profiles and assign relevance scores, selecting only high-impact contextual elements that fit within the model's context window. In the second phase, CPRVul integrates the target function, the selected context, and auxiliary vulnerability metadata to generate reasoning traces, which are used to fine-tune LLMs for reasoning-based vulnerability detection. We evaluate CPRVul on three high-quality vulnerability datasets: PrimeVul, TitanVul, and CleanVul. Across all datasets, CPRVul consistently outperforms function-only baselines, achieving accuracies ranging from 64.94% to 73.76%, compared to 56.65% to 63.68% for UniXcoder. Specifically, on the challenging PrimeVul benchmark, CPRVul achieves 67.78% accuracy, outperforming prior state-of-the-art approaches, improving accuracy from 55.17% to 67.78% (22.9% improvement). Our ablations further show that neither raw context nor processed context alone benefits strong code models; gains emerge only when processed context is paired with structured reasoning.

cs.CR↗

arXiv2026

Legendre Memory Unit with A Multi-Slice Compensation Model for Short-Term Wind Speed Forecasting Based on Wind Farm Cluster Data

With more wind farms clustered for integration, the short-term wind speed prediction of such wind farm clusters is critical for normal operation of power systems. This paper focuses on achieving accurate, fast, and robust wind speed prediction by full use of cluster data with spatial-temporal correlation. First, weighted mean filtering (WMF) is applied to denoise wind speed data at the single-farm level. The Legendre memory unit (LMU) is then innovatively applied for the wind speed prediction, in combination with the Compensating Parameter based on Kendall rank correlation coefficient (CPK) of wind farm cluster data, to construct the multi-slice LMU (MSLMU). Finally, an innovative ensemble model WMF-CPK-MSLMU is proposed herein, with three key blocks: data pre-processing, forecasting, and multi-slice compensation. Advantages include: 1) LMU jointly models linear and nonlinear dependencies among farms to capture spatial-temporal correlations through backpropagation; 2) MSLMU enhances forecasting by using CPK-derived weights instead of random initialization, allowing spatial correlations to fully activate hidden nodes across clustered wind farms.; 3) CPK adaptively weights the compensation model in MSLMU and complements missing data spatially, to facilitate the whole model highly accurate and robust. Test results on different wind farm clusters indicate the effectiveness and superiority of proposed ensemble model WMF-CPK-MSLMU in the short-term prediction of wind farm clusters compared to the existing models.

cs.LG↗

arXiv2026

Out of Distribution, Out of Luck: How Well Can LLMs Trained on Vulnerability Datasets Detect Top 25 CWE Weaknesses?

Automated vulnerability detection research has made substantial progress, yet its real-world impact remains limited. Prior work found that current vulnerability datasets suffer from issues including label inaccuracy rates of 20%-71%, extensive duplication, and poor coverage of critical Common Weakness Enumeration (CWE). These issues create a significant generalization gap where models achieve misleading In-Distribution (ID) accuracies (testing on splits from the same dataset) by exploiting spurious correlations rather than learning true vulnerability patterns. To address these limitations, we present a three-part solution. First, we introduce BenchVul, which is a manually curated and balanced test dataset covering the MITRE Top 25 Most Dangerous CWEs, to enable fair model evaluation. Second, we construct a high-quality training dataset, TitanVul, comprising 38,548 functions by aggregating seven public sources and applying deduplication and validation using a novel multi-agent LLM pipeline. Third, we propose a Realistic Vulnerability Generation (RVG) pipeline, which synthesizes context-aware vulnerability examples for underrepresented but critical CWE types through simulated development workflows. Our evaluation reveals that In-Distribution (ID) performance does not reliably predict Out-of-Distribution (OOD) performance on BenchVul. For example, a model trained on BigVul achieves the highest 0.703 ID accuracy but fails on BenchVul's real-world samples (0.493 OOD accuracy). Conversely, a model trained on our TitanVul achieves the highest OOD performance on both the real-world (0.881) and synthesized (0.785) portions of BenchVul, improving upon the next-best performing dataset by 5.3% and 11.8% respectively, despite a modest ID score (0.590). Augmenting TitanVul with our RVG further boosts this leading OOD performance, improving accuracy on real-world data by 5.8% (to 0.932).

cs.CR↗

arXiv2026

PenForge: On-the-Fly Expert Agent Construction for Automated Penetration Testing

Penetration testing is essential for identifying vulnerabilities in web applications before real adversaries can exploit them. Recent work has explored automating this process with Large Language Model (LLM)-powered agents, but existing approaches either rely on a single generic agent that struggles in complex scenarios or narrowly specialized agents that cannot adapt to diverse vulnerability types. We therefore introduce PenForge, a framework that dynamically constructs expert agents during testing rather than relying on those prepared beforehand. By integrating automated reconnaissance of potential attack surfaces with agents instantiated on the fly for context-aware exploitation, PenForge achieves a 30.0% exploit success rate (12/40) on CVE-Bench in the particularly challenging zero-day setting, which is a 3 times improvement over the state-of-the-art. Our analysis also identifies three opportunities for future work: (1) supplying richer tool-usage knowledge to improve exploitation effectiveness; (2) extending benchmarks to include more vulnerabilities and attack types; and (3) fostering developer trust by incorporating explainable mechanisms and human review. As an emerging result with substantial potential impact, PenForge embodies the early-stage yet paradigm-shifting idea of on-the-fly agent construction, marking its promise as a step toward scalable and effective LLM-driven penetration testing.

cs.SE↗

arXiv2025

Aligning Academia with Industry: An Empirical Study of Industrial Needs and Academic Capabilities in AI-Driven Software Engineering

The rapid advancement of large language models (LLMs) is fundamentally reshaping software engineering (SE), driving a paradigm shift in both academic research and industrial practice. While top-tier SE venues continue to show sustained or emerging focus on areas like automated testing and program repair, with researchers worldwide reporting continuous performance gains, the alignment of these academic advances with real industrial needs remains unclear. To bridge this gap, we first conduct a systematic analysis of 1,367 papers published in FSE, ASE, and ICSE between 2022 and 2025, identifying key research topics, commonly used benchmarks, industrial relevance, and open-source availability. We then carry out an empirical survey across 17 organizations, collecting 282 responses on six prominent topics, i.e., program analysis, automated testing, code generation/completion, issue resolution, pre-trained code models, and dependency management, through structured questionnaires. By contrasting academic capabilities with industrial feedback, we derive seven critical implications, highlighting under-addressed challenges in software requirements and architecture, the reliability and explainability of intelligent SE approaches, input assumptions in academic research, practical evaluation tensions, and ethical considerations. This study aims to refocus academic attention on these important yet under-explored problems and to guide future SE research toward greater industrial impact.

cs.SE↗

arXiv2025

RDTF: Resource-efficient Dual-mask Training Framework for Multi-frame Animated Sticker Generation

Recently, significant advancements have been achieved in video generation technology, but applying it to resource-constrained downstream tasks like multi-frame animated sticker generation (ASG) characterized by low frame rates, abstract semantics, and long tail frame length distribution-remains challenging. Parameter-efficient fine-tuning (PEFT) techniques (e.g., Adapter, LoRA) for large pre-trained models suffer from insufficient fitting ability and source-domain knowledge interference. In this paper, we propose Resource-Efficient Dual-Mask Training Framework (RDTF), a dedicated solution for multi-frame ASG task under resource constraints. We argue that training a compact model from scratch with million-level samples outperforms PEFT on large models, with RDTF realizing this via three core designs: 1) a Discrete Frame Generation Network (DFGN) optimized for low-frame-rate ASG, ensuring parameter efficiency; 2) a dual-mask based data utilization strategy to enhance the availability and diversity of limited data; 3) a difficulty-adaptive curriculum learning method that decomposes sample entropy into static and adaptive components, enabling easy-to-difficult training convergence. To provide high-quality data support for RDTFs training from scratch, we construct VSD2M-a million-level multi-modal animated sticker dataset with rich annotations (static and animated stickers, action-focused text descriptions)-filling the gap of dedicated animated data for ASG task. Experiments demonstrate that RDTF is quantitatively and qualitatively superior to state-of-the-art PEFT methods (e.g., I2V-Adapter, SimDA) on ASG tasks, verifying the feasibility of our framework under resource constraints.

cs.MM↗

arXiv2025

mmE-Loc: Facilitating Accurate Drone Landing with Ultra-High-Frequency Localization

For precise, efficient, and safe drone landings, ground platforms should real-time, accurately locate descending drones and guide them to designated spots. While mmWave sensing combined with cameras improves localization accuracy, lower sampling frequency of traditional frame cameras compared to mmWave radar creates bottlenecks in system throughput. In this work, we upgrade traditional frame camera with event camera, a novel sensor that harmonizes in sampling frequency with mmWave radar within ground platform setup, and introduce mmE-Loc, a high-precision, low-latency ground localization system designed for precise drone landings. To fully exploit the \textit{temporal consistency} and \textit{spatial complementarity} between these two modalities, we propose two innovative modules: \textit{(i)} the Consistency-instructed Collaborative Tracking module, which further leverages the drone's physical knowledge of periodic micro-motions and structure for accurate measurements extraction, and \textit{(ii)} the Graph-informed Adaptive Joint Optimization module, which integrates drone motion information for efficient sensor fusion and drone localization. Real-world experiments conducted in landing scenarios with a drone delivery company demonstrate that mmE-Loc significantly outperforms state-of-the-art methods in both accuracy and latency.

cs.RO↗

arXiv2025

From Events to Trending: A Multi-Stage Hotspots Detection Method Based on Generative Query Indexing

LLM-based conversational systems have become a popular gateway for information access, yet most existing chatbots struggle to handle news-related trending queries effectively. To improve user experience, an effective trending query detection method is urgently needed to enable differentiated processing of such target traffic. However, current research on trending detection tailored to the dialogue system scenario remains largely unexplored, and methods designed for traditional search engines often underperform in conversational contexts due to radically distinct query distributions and expression patterns. To fill this gap, we propose a multi-stage framework for trending detection, which achieves systematic optimization from both offline generation and online identification perspectives. Specifically, our framework first exploits selected hot events to generate index queries, establishing a key bridge between static events and dynamic user queries. It then employs a retrieval matching mechanism for real-time online detection of trending queries, where we introduce a cascaded recall and ranking architecture to balance detection efficiency and accuracy. Furthermore, to better adapt to the practical application scenario, our framework adopts a single-recall module as a cold-start strategy to collect online data for fine-tuning the reranker. Extensive experiments demonstrate that our framework significantly outperforms baseline methods in both offline evaluations and online A/B tests, and user satisfaction is relatively improved by 27\% in terms of positive-negative feedback ratio.

cs.IR↗

arXiv2025

Scalable protocol to coherence estimation from scarce data: Theory and experiment

Key quantum features like coherence are the fundamental resources enabling quantum advantages and ascertaining their presence in quantum systems is crucial for developing quantum technologies. This task, however, faces severe challenges in the noisy intermediate-scale quantum era. On one hand, experimental data are typically scarce, rendering full state reconstruction infeasible. On the other hand, these features are usually quantified by highly nonlinear functionals that elude efficient estimations via existing methods. In this work, we propose a scalable protocol for estimating coherence from scarce data and further experimentally demonstrate its practical utility. The key innovation here is to relax the potentially NP-hard coherence estimation problem into a computationally efficient optimization. This renders the computational cost in our protocol insensitive to the system size, in sharp contrast to the exponential growth in traditional methods. This work opens a novel route toward estimating coherence of large-scale quantum systems under data-scarce conditions.

quant-ph↗

arXiv2025

An LLM-as-Judge Metric for Bridging the Gap with Human Evaluation in SE Tasks

Large Language Models (LLMs) and other automated techniques have been increasingly used to support software developers by generating software artifacts such as code snippets, patches, and comments. However, accurately assessing the correctness of these generated artifacts remains a significant challenge. On one hand, human evaluation provides high accuracy but is labor-intensive and lacks scalability. On the other hand, many automatic evaluation metrics are scalable and require minimal human effort, but they often fail to accurately reflect the actual correctness of generated software artifacts. In this paper, we present SE-Jury, the first evaluation metric for LLM-as-Ensemble-Judge specifically designed to accurately assess the correctness of generated software artifacts. SE-Jury first defines five distinct evaluation strategies, each implemented by an independent judge. A dynamic team selection mechanism then identifies the most appropriate subset of judges as a team to produce a final correctness score through ensembling. We evaluate SE-Jury across a diverse set of software engineering (SE) benchmarks that span three popular SE tasks: code generation, automated program repair, and code summarization. Results demonstrate that SE-Jury consistently achieves a higher correlation with human judgments, with improvements ranging from 29.6% to 140.8% over existing automatic metrics. SE-Jury reaches agreement levels with human annotators that are close to inter-annotator agreement in code generation and program repair. These findings underscore SE-Jury's potential as a scalable and reliable alternative to human evaluation in these SE tasks.

cs.SE↗