相关论文: FoC: Figure out the Cryptographic Functions in Str…

Decompilation is widely used in reverse engineering to recover high-level language code from binary executables. While recent approaches leveraging Large Language Models (LLMs) have shown promising progress, they typically treat assembly…

Dead code introduces several challenges in software development, such as increased binary size and maintenance difficulties. It can also obscure logical errors and be exploited for obfuscation in malware. For LLM-based code-related tasks,…

Binary code similarity detection (BCSD) is widely used in various binary analysis tasks such as vulnerability search, malware detection, clone detection, and patch analysis. Recent studies have shown that the learning-based binary code…

Large language models (LLMs) need reliable test-time control of hallucinations. Existing conformal methods for LLMs typically provide only \emph{marginal} guarantees and rely on a single global threshold, which can under-cover hard prompts,…

Detecting fraud in financial transactions typically relies on tabular models that demand heavy feature engineering to handle high-dimensional data and offer limited interpretability, making it difficult for humans to understand predictions.…

Tokenization is associated with many poorly understood shortcomings in language models (LMs), yet remains an important component for long sequence scaling purposes. This work studies how tokenization impacts model performance by analyzing…

A function inlining optimization is a widely used transformation in modern compilers, which replaces a call site with the callee's body in need. While this transformation improves performance, it significantly impacts static features such…

Node classification is a fundamental task in graph analysis, with broad applications across various fields. Recent breakthroughs in Large Language Models (LLMs) have enabled LLM-based approaches for this task. Although many studies…

Binary analysis is a core component of many critical security tasks, including reverse engineering, malware analysis, and vulnerability detection. Manual analysis is often time-consuming, but identifying commonly-used or previously-seen…

We build \textbf{AICrypto}, a comprehensive benchmark designed to evaluate the cryptography capabilities of large language models (LLMs). The benchmark comprises 135 multiple-choice questions, 150 capture-the-flag challenges, and 30 proof…

Vulnerability detection is crucial for maintaining software security, and recent research has explored the use of Language Models (LMs) for this task. While LMs have shown promising results, their performance has been inconsistent across…

Despite various approaches being employed to detect vulnerabilities, the number of reported vulnerabilities shows an upward trend over the years. This suggests the problems are not caught before the code is released, which could be caused…

Visual reasoning is crucial for multimodal large language models (MLLMs) to address complex chart queries, yet high-quality rationale data remains scarce. Existing methods leveraged (M)LLMs for data generation, but direct prompting often…

Fine-tuning large language models (LLMs) with domain-specific instructions has emerged as an effective method to enhance their domain-specific understanding. Yet, there is limited work that examines the core characteristics acquired during…

General-purpose Large Language Models (LLMs) are frequently fine-tuned through supervised fine-tuning (SFT) to enhance performance in specific domains. Better results can be achieved by distilling the chain-of-thought of a larger model at…

Large Language Models (LLMs) are being extensively used for cybersecurity purposes. One of them is the detection of vulnerable codes. For the sake of efficiency and effectiveness, compression and fine-tuning techniques are being developed,…

Binary analysis of software is a critical step in cyber forensics applications such as program vulnerability assessment and malware detection. This involves interpreting instructions executed by software and often necessitates converting…

Deep learning malware detectors achieve high classification accuracy but suffer from severe interpretability limitations, typically returning probabilistic verdicts that lack forensic context. We introduce AsmRAG, a framework performing…

Restructuring compilers use dependence analysis to prove that the meaning of a program is not changed by a transformation. A well-known limitation of dependence analysis is that it examines only the memory locations read and written by a…

Code Linting tools are vital for detecting potential defects in Verilog code. However, the limitations of traditional Linting tools are evident in frequent false positives and redundant defect reports. Recent advancements in large language…