arXiv subjects

Dianxiang Xu

Publications and source records attributed to Dianxiang Xu.

5 recordsLinked to original sources

arXiv2026

Scalable PII Discovery in Mobile App Databases via Hypothesis-Driven Search

Discovering personally identifiable information (PII) in mobile forensic databases is difficult because the relevant table-column regions are unknown, distributed across heterogeneous SQLite schemas, and may contain values embedded in free-text or semi-structured fields. We present a hypothesis-driven framework that treats PII localization as bounded, adaptive search under uncertainty. An agent ranks candidate table-column regions, probes sampled values, and maintains a memory of prior evidence, confidence scores, and decisions to refine subsequent hypotheses. The framework separates lightweight PII exploration from targeted extraction, normalization, and deduplication over validated regions, thereby limiting exhaustive inspection to regions supported by sampled evidence. We evaluate the framework on 25 SQLite databases from 10 Android and iOS applications in the Cellebrite CTF corpus, targeting email addresses, phone numbers, domain names, person names, and postal addresses. Against a corpus-level distinct ground-truth set of 3,751 entities, Gemini 2.5 Pro achieves 94.5% F1 while reducing the effective extraction search space by 79.9% on average. Results across 12 model backends show strong performance among several frontier models, but substantial sensitivity to model capability.

cs.CR↗

arXiv2026

AutoACSL: Synthesizing ACSL Specifications by Integrating LLMs with CPG-Based Static Analysis

Generating formal specifications for C programs remains a challenge in formal verification due to the manual effort, expertise, and semantic precision required. While recent advancements in large language models (LLMs) offer promise in automating specification synthesis, current approaches often lack semantic depth and produce unverifiable or incomplete contracts. To address these limitations, we introduce AutoACSL, a novel framework that integrates LLM prompting with semantic features extracted from Code Property Graphs (CPGs). AutoACSL performs static analyses to extract key semantic elements, including arithmetic operations, loop and recursion structures, and return value propagation, which are encoded into structured prompts. These prompts enable the LLM not only to generate normal behavioral specifications but also to include constraints that prevent inputs leading to runtime errors. AutoACSL employs a feedback-driven synthesis loop, where candidate specifications are verified using Frama-C/WP and refined iteratively until verification succeeds or a termination condition is met. Evaluated on 604 programs drawn from diverse datasets, AutoACSL achieves a 98% specification generation success ratio and a 96% full proof ratio when paired with Gemini-3. Compared to a code-only baseline, AutoACSL improves the full proof ratio by 24.7% to 51.7% across four LLMs (GPT-o4 Mini, GPT-5.2, Grok-4.1, and Gemini-3), demonstrating that integrating large language models with CPG-based static analysis substantially enhances both generation robustness and verification effectiveness for automated ACSL specification synthesis.

cs.AI↗

arXiv2025

HALURust: Exploiting Hallucinations of Large Language Models to Detect Vulnerabilities in Rust

As an emerging programming language, Rust has rapidly gained popularity and recognition among developers due to its strong emphasis on safety. It employs a unique ownership system and safe concurrency practices to ensure robust safety. Despite these safeguards, security in Rust still presents challenges. Since 2018, 442 Rust-related vulnerabilities have been reported in real-world applications. The limited availability of data has resulted in existing vulnerability detection tools performing poorly in real-world scenarios, often failing to adapt to new and complex vulnerabilities. This paper introduces HALURust, a novel framework that leverages hallucinations of large language models (LLMs) to detect vulnerabilities in real-world Rust scenarios. HALURust leverages LLMs' strength in natural language generation by transforming code into detailed vulnerability analysis reports. The key innovation lies in prompting the LLM to always assume the presence of a vulnerability. If the code sample is vulnerable, the LLM provides an accurate analysis; if not, it generates a hallucinated report. By fine-tuning LLMs on these hallucinations, HALURust can effectively distinguish between vulnerable and non-vulnerable code samples. HALURust was evaluated on a dataset of 81 real-world vulnerabilities, covering 447 functions and 18,691 lines of code across 54 applications. It outperformed existing methods, achieving an F1 score of 77.3%, with over 10% improvement. The hallucinated report-based fine-tuning improved detection by 20\% compared to traditional code-based fine-tuning. Additionally, HALURust effectively adapted to unseen vulnerabilities and other programming languages, demonstrating strong generalization capabilities.

cs.CR↗

arXiv2025

Detecting Code Vulnerabilities with Heterogeneous GNN Training

Detecting vulnerabilities in source code is a critical task for software security assurance. Graph Neural Network (GNN) machine learning can be a promising approach by modeling source code as graphs. Early approaches treated code elements uniformly, limiting their capacity to model diverse relationships that contribute to various vulnerabilities. Recent research addresses this limitation by considering the heterogeneity of node types and using Gated Graph Neural Networks (GGNN) to aggregate node information through different edge types. However, these edges primarily function as conduits for passing node information and may not capture detailed characteristics of distinct edge types. This paper presents Inter-Procedural Abstract Graphs (IPAGs) as an efficient, language-agnostic representation of source code, complemented by heterogeneous GNN training for vulnerability prediction. IPAGs capture the structural and contextual properties of code elements and their relationships. We also propose a Heterogeneous Attention GNN (HAGNN) model that incorporates multiple subgraphs capturing different features of source code. These subgraphs are learned separately and combined using a global attention mechanism, followed by a fully connected neural network for final classification. The proposed approach has achieved up to 96.6% accuracy on a large C dataset of 108 vulnerability types and 97.8% on a large Java dataset of 114 vulnerability types, outperforming state-of-the-art methods. Its applications to various real-world software projects have also demonstrated low false positive rates.

cs.CR↗

arXiv2020

Assessing Holistic Impacts of Major Events on the Bitcoin Blockchain Network

As the pioneer of blockchain technology, Bitcoin is the most popular cryptocurrency to date. Given its dramatic price spikes (and crashes) along with the never-ending news from SEC regulations to security breaches, there seems to be a lack of understanding about the dynamics of cryptocurrencies. These dynamics are believed to be affected by various political, security, financial, and regulatory events. In this paper, we present an efficient framework for holistic analysis of cryptocurrency fluctuations by introducing the Impact-Score metric to distinguish event-induced changes from normal variations. We have applied our framework to 16 major worldwide events and the Bitcoin blockchain network (defined as Bitcoin transaction and users, blockchain data, and memory pool data) from 2016-2018. The results show that a majority of the events are correlated with substantial network changes. We observed roughly generalizable correlations between event types (e.g. financial events) and sub-structures of the Bitcoin blockchain network. Subgroups of these events have strongly consistent temporal impacts on specific facets (e.g. activity or fees) of the Bitcoin ecosystem. Furthermore, we demonstrate the robustness of our process by correlating a majority of spikes in network/subnetwork change with major events.

cs.CY↗