arXiv subjects

Lingfeng Chen

Publications and source records attributed to Lingfeng Chen.

10 recordsLinked to original sources

arXiv2026

Directed Symbolic Execution for Vulnerability Discovery: An LLM-Guided Approach in KLEE

Symbolic execution effectively discovers security violations but suffers from path explosion. Engines like KLEE therefore use path prioritization heuristics to order state exploration, typically optimizing code coverage. However, path prioritization can become trapped in cyclic control-flow regions, where repeated branching consumes the exploration budget before exploration reaches vulnerable code beyond these cyclic regions. We propose KLEECopilot, a Large Language Model (LLM)-guided directed symbolic execution approach built on KLEE. KLEECopilot uses LLMs to mark potentially vulnerable code and guide path prioritization. It also integrates loop-exit prioritization to escape potentially non-vulnerable cycles and progress toward deeper vulnerabilities. Compared with baselines such as Empc, KLEECopilot improves basic block coverage by 42.24% and line coverage by 125.82%. It discovers 1,335 total violations and 87 unique violations, outperforming the second-best baseline by 32.2% in total violations and Empc by 24.3% in unique violations. Although KLEECopilot is sensitive to model family, it exhibits only marginal sensitivity to model scale, supporting the efficacy of integrating security semantics and loop-exit prioritization. Ablation studies further show that individual components contribute to effectiveness: alternative configurations involving searchers, internal components, marking sources, and prompt variants yield only 54--61 unique violations, while KLEECopilot maintains competitive code coverage.

cs.SE↗

arXiv2026

A Causal Graph Approach to Oppositional Narrative Analysis

Current methods for textual analysis rely on data annotated within predefined ontologies, often embedding human bias within black-box models. Despite achieving near-perfect performance, these approaches exploit unstructured, linear pattern recognition rather than modeling the structured interactions between entities that naturally emerge in discourse. In this work, we propose a graph-based framework for the detection, analysis, and classification of oppositional narratives and their underlying entities by representing narratives as entity-interaction graphs. Moreover, by incorporating causal estimation at the node level, our approach derives a causal representation of each contribution to the final classification by distilling the constructed sentence graph into a minimal causal subgraph. Building upon this representation, we introduce a classification pipeline that outperforms existing approaches to oppositional thinking classification task.

cs.CL↗

arXiv2026

More Code, Less Reuse: Investigating Code Quality and Reviewer Sentiment towards AI-generated Pull Requests

Large Language Model (LLM) Agents are advancing quickly, with the increasing leveraging of LLM Agents to assist in development tasks such as code generation. While LLM Agents accelerate code generation, studies indicate they may introduce adverse effects on development. However, existing metrics solely measure pass rates, failing to reflect impacts on long-term maintainability and readability, and failing to capture human intuitive evaluations of PR. To increase the comprehensiveness of this problem, we investigate and evaluate the characteristics of LLM to know the pull requests' characteristics beyond the pass rate. We observe the code quality and maintainability within PRs based on code metrics to evaluate objective characteristics and developers' reactions to the pull requests from both humans and LLM's generation. Evaluation results indicate that LLM Agents frequently disregard code reuse opportunities, resulting in higher levels of redundancy compared to human developers. In contrast to the quality issues, our emotions analysis reveals that reviewers tend to express more neutral or positive emotions towards AI-generated contributions than human ones. This disconnect suggests that the surface-level plausibility of AI code masks redundancy, leading to the silent accumulation of technical debt in real-world development environments. Our research provides insights for improving human-AI collaboration.

cs.SE↗

arXiv2025

Teaching large language models to see in radar: aspect-distributed prototypes for few-shot HRRP ATR

High-resolution range profiles (HRRPs) play a critical role in automatic target recognition (ATR) due to their richinformationregarding target scattering centers (SCs), which encapsulate the geometric and electromagnetic characteristics of thetarget.Under few-shot circumstances, traditional learning-based methods often suffer from overfitting and struggle togeneralizeeffectively. The recently proposed HRRPLLM, which leverages the in-context learning (ICL) capabilities of largelanguagemodels (LLMs) for one-shot HRRP ATR, is limited in few-shot scenarios. This limitation arises because it primarilyutilizesthe distribution of SCs for recognition while neglecting the variance of the samples caused by aspect sensitivity. Thispaperproposes a straightforward yet effective Aspect-Distributed Prototype (ADP) strategy for LLM-based ATRunder few-shotconditions to enhance aspect robustness. Experiments conducted on both simulated and measured aircraft electromagneticdatasets demonstrate that the proposed method significantly outperforms current benchmarks.

eess.SP↗

arXiv2025

Large Language Models Can Achieve Explainable and Training-Free One-shot HRRP ATR

This letter introduces a pioneering, training-free and explainable framework for High-Resolution Range Profile (HRRP) automatic target recognition (ATR) utilizing large-scale pre-trained Large Language Models (LLMs). Diverging from conventional methods requiring extensive task-specific training or fine-tuning, our approach converts one-dimensional HRRP signals into textual scattering center representations. Prompts are designed to align LLMs' semantic space for ATR via few-shot in-context learning, effectively leveraging its vast pre-existing knowledge without any parameter update. We make our codes publicly available to foster research into LLMs for HRRP ATR.

eess.SP↗

arXiv2025

Noise-Robustness Through Noise: A Framework combining Asymmetric LoRA with Poisoning MoE

Current parameter-efficient fine-tuning methods for adapting pre-trained language models to downstream tasks are susceptible to interference from noisy data. Conventional noise-handling approaches either rely on laborious data pre-processing or employ model architecture modifications prone to error accumulation. In contrast to existing noise-process paradigms, we propose a noise-robust adaptation method via asymmetric LoRA poisoning experts (LoPE), a novel framework that enhances model robustness to noise only with generated noisy data. Drawing inspiration from the mixture-of-experts architecture, LoPE strategically integrates a dedicated poisoning expert in an asymmetric LoRA configuration. Through a two-stage paradigm, LoPE performs noise injection on the poisoning expert during fine-tuning to enhance its noise discrimination and processing ability. During inference, we selectively mask the dedicated poisoning expert to leverage purified knowledge acquired by normal experts for noise-robust output. Extensive experiments demonstrate that LoPE achieves strong performance and robustness purely through the low-cost noise injection, which completely eliminates the requirement of data cleaning.

cs.LG↗

arXiv2025

Few-shot Human Motion Recognition through Multi-Aspect mmWave FMCW Radar Data

Radar human motion recognition methods based on deep learning models has been a heated spot of remote sensing in recent years, yet the existing methods are mostly radial-oriented. In practical application, the test data could be multi-aspect and the sample number of each motion could be very limited, causing model overfitting and reduced recognition accuracy. This paper proposed channel-DN4, a multi-aspect few-shot human motion recognition method. First, local descriptors are introduced for a precise classification metric. Moreover, episodic training strategy was adopted to reduce model overfitting. To utilize the invariant sematic information in multi-aspect conditions, we considered channel attention after the embedding network to obtain precise implicit high-dimensional representation of sematic information. We tested the performance of channel-DN4 and methods for comparison on measured mmWave FMCW radar data. The proposed channel-DN4 produced competitive and convincing results, reaching the highest 87.533% recognition accuracy in 3-way 10-shot condition while other methods suffer from overfitting. Codes are available at: https://github.com/MountainChenCad/channel-DN4

eess.SP↗

arXiv2025

CveBinarySheet: A Comprehensive Pre-built Binaries Database for IoT Vulnerability Analysis

Binary Static Code Analysis (BSCA) is a pivotal area in software vulnerability research, focusing on the precise localization of vulnerabilities within binary executables. Despite advancements in BSCA techniques, there is a notable scarcity of comprehensive and readily usable vulnerability datasets tailored for diverse environments such as IoT, UEFI, and MCU firmware. To address this gap, we present CveBinarySheet, a meticulously curated database containing 1033 CVE entries spanning from 1999 to 2024. Our dataset encompasses 16 essential third-party components, including busybox and curl, and supports five CPU architectures: x86-64, i386, MIPS, ARMv7, and RISC-V64. Each precompiled binary is available at two compiler optimization levels (O0 and O3), facilitating comprehensive vulnerability analysis under different compilation scenarios. By providing detailed metadata and diverse binary samples, CveBinarySheet aims to accelerate the development of state-of-the-art BSCA tools, binary similarity analysis, and vulnerability matching applications.

cs.CR↗

arXiv2024

A Deep Learning-Based Target Radial Length Estimation Method through HRRP Sequence

This paper introduces an innovative deep learning-based method for end-to-end target radial length estimation from HRRP (High Resolution Range Profile) sequences. Firstly, the HRRP sequences are normalized and transformed into GAF (Gram Angular Field) images to effectively capture and utilize the temporal information. Subsequently, these GAF images serve as the input for a pretrained ResNet-101 model, which is then fine-tuned for target radial length estimation. The simulation results show that compared to traditional threshold method and simple networks e.g. one-dimensional CNN (Convolutional Neural Network), the proposed method demonstrates superior noise resistance and higher accuracy under low SNR (Signal-to-Noise Ratio) conditions.

eess.SP↗

arXiv2024

HRRPGraphNet: Make HRRPs to Be Graphs for Efficient Target Recognition

High Resolution Range Profiles (HRRP) have become a key area of focus in the domain of Radar Automatic Target Recognition (RATR). Despite the success of deep learning based HRRP recognition, these methods needs a large amount of training samples to generate good performance, which could be a severe challenge under non-cooperative circumstances. Currently, deep learning based models treat HRRP as sequences, which may lead to ignorance of the internal relationship of range cells. This letter introduces HRRPGraphNet, whose pivotal innovation is the transformation of HRRP data into a novel graph structure, utilizing a range cell amplitude(hyphen)based node vector and a range(hyphen)relative adjacency matrix. This graph(hyphen)based approach facilitates both local feature extraction via one(hyphen)dimensional convolution layers, global feature extraction through a graph convolution layer and a attention module. Experiments on the aircraft electromagnetic simulation dataset confirmed HRRPGraphNet superior accuracy and robustness, particularly in limited training sample environments, underscoring the potential of graph(hyphen)driven innovations in HRRP(hyphen)based RATR.

eess.SP↗