arXiv subjects

Sungbin Park

Publications and source records attributed to Sungbin Park.

4 recordsLinked to original sources

arXiv2026

CLEAR: Causal Context-Based Agentic Reasoning for Vulnerability Detection

Detecting source code vulnerabilities is increasingly difficult as modern security flaws are rooted in complex causal dependencies between execution flows, control conditions, and program states. Despite recent advances in Large Language Models (LLMs) and multi-agent frameworks, existing approaches primarily address superficial similarities between benign and vulnerable functions while failing to capture the complex causal dependencies inherent in security flaws. To address these limitations, we propose Causal Context-based Agentic Reasoning (CLEAR), a novel multi-agent vulnerability detection framework integrated with a causal knowledge graph. CLEAR systematically constructs a Vulnerability Causal Knowledge Graph (VCKG) that models the causal chains between entrypoints, preconditions, root causes, and fix intents across vulnerability instances. Leveraging this structured knowledge, four specialized agents, including the Collector, Claim, Critic, and Judge, collaboratively verify vulnerability hypotheses through retrieved causal contexts. Experimental results on C/C++ and Java vulnerability benchmarks demonstrate that CLEAR improves Pair-Correct (P-C) performance by 130.7% and 71.56% over state-of-the-art approaches, demonstrating the effectiveness of causal knowledge graph-guided reasoning for automated vulnerability detection.

cs.CR↗

arXiv2026

An Evaluation of Large Language Models for Detection of Malicious Python Packages

Modern software development relies on open-source package repositories. Attackers use these to distribute malicious packages. Large Language Models (LLMs) can automatically detect these packages, but their ability to pinpoint specific malicious behaviors remains unclear. We evaluate 13 LLMs on two tasks using a dataset of 4,070 PyPI packages (370 malicious, 3,700 benign). The first task detects whether a package is malicious. The second identifies specific malicious indicators (lines of code). We evaluate each LLM across five prompt strategies and three temperatures. For the first task, LLMs achieve mean F1 scores from 0.40 to 0.99, detecting most malicious packages but frequently flagging safe ones. For the second task, LLMs achieve a weighted F1 score of 0.69 for recognizing behavior types, dropping to 0.48 when identifying specific indicators. LLMs recognize standard code patterns but miss indicators requiring broader context or the author's intent. LLMs also report absent indicators. Evaluating the association between performance and model size, context width, prompt strategy, temperature, and code complexity reveals only code complexity has a meaningful impact: longer packages are harder to analyze. We recommend using LLMs for initial triage to flag suspicious packages for human review, rather than identifying specific malicious mechanisms.

cs.CR↗

arXiv2025

On the Boltzmann-Fermi-Dirac Equation for Hard Potential: Global Existence and Uniqueness, Gaussian Lower Bound, and Moment Estimates

In this paper, we study the global existence and uniqueness, Gaussian lower bound, and moment estimates in the spatially homogeneous Boltzmann equation for Fermi-Dirac particles for hard potential ($0\leq \gamma\leq 2$) with angular cutoff $b$. Our results extend classical results to the Boltzmann-Fermi-Dirac setting. In detail, (1) we show existence, uniqueness, and $L^1_2$ stability of global-in-time solutions of the Boltzmann-Fermi-Dirac equation. (2) Assuming the solution is not a saturated equilibrium, we prove creation of a Gaussian lower bound for the solution. (3) We prove creation and propagation of $L^1$ polynomial and exponential moments of the solution under additional assumptions on the angular kernel $b$ and $0<\gamma\leq 2$. (4) Finally, we show propagation of $L^\infty$ Gaussian and polynomial upper bounds when $b$ is constant and $0<\gamma\leq 1$.

math.AP↗

arXiv2024

Ill-posedness of the Boltzmann-BGK model in the exponential class

BGK (Bhatnagar-Gross-Krook) model is a relaxation-type model of the Boltzmann equation, which is popularly used in place of the Boltzmann equation in physics and engineering. In this paper, we address the ill-posedness problem for the BGK model, in which the solution instantly escapes the initial solution space. For this, we propose two ill-posedness scenarios, namely, the homogeneous and the inhomogeneous ill-posedness mechanisms. In the former case, we find a class of spatially homogeneous solutions to the BGK model, where removing the small velocity part of the initial data triggers ill-posedness by increasing temperature. For the latter, we construct a spatially inhomogeneous solution to the BGK model such that the local temperature constructed from the solution has a polynomial growth in spatial variable. These ill-posedness properties for the BGK model pose a stark contrast with the Boltzmann equation for which the solution map is, at least for a finite time, stable in the corresponding solution spaces.

math.AP↗