Searcharxiv⌕ Search

arXiv subjects

Alexander Küchler

Publications and source records attributed to Alexander Küchler.

3 recordsLinked to original sources

TRIAGE-CPG: A Cross-Model Study of Budgeted Static Malware Triage with Large Language Models

When triaging unknown binaries, security analysts must decide which samples to clear as benign, flag as malicious, or escalate for deeper analysis. Large Language Models (LLMs) could support these decisions by interpreting decompiled code, but a binary can contain hundreds or thousands of functions, making exhaustive LLM analysis impractical. We study how current LLMs behave when static triage is formulated as budgeted evidence acquisition: which functions they inspect and how they trade off benign clearance, malware detection, and escalation. To enable a controlled comparison, we implement TRIAGE-CPG, a fixed pipeline over a code property graph (CPG) of a decompiled binary. An LLM-free heuristic selects seed functions, an agent expands the resulting evidence dossier under a fixed budget, and a reporting stage produces a benign, suspicious, or malicious verdict together with a behavioral report. We evaluate eight closed-source and open-weight models on 1,000 Windows PE binaries, using a 600-sample test split and the same zero-shot protocol for every model. We assess the ternary verdicts under both a strict binary reading and triage balanced accuracy (tBA), which credits malware that is flagged or escalated and benign samples only when cleared. After analyzing about 40 of a mean 1,000 functions per binary, the highest-scoring model reaches a strict balanced accuracy of 0.805 and a tBA of 0.855, flagging 65% of malware, escalating another 12%, and clearing 94% of benign samples. The models implement different triage policies: high-specificity models produce small, malware-rich escalation queues, whereas recall-oriented models escalate or flag much more broadly. Both closed-source and open-weight models appear across this spectrum. Our results identify no universal deployment configuration: model choice itself determines the clear/flag/escalate trade-off under limited static evidence.

cs.CR↗

A Uniform Representation of Classical and Quantum Source Code for Static Code Analysis

The emergence of quantum computing raises the question of how to identify (security-relevant) programming errors during development. However, current static code analysis tools fail to model information specific to quantum computing. In this paper, we identify this information and propose to extend classical code analysis tools accordingly. Among such tools, we identify the Code Property Graph to be very well suited for this task as it can be easily extended with quantum computing specific information. For our proof of concept, we implemented a tool which includes information from the quantum world in the graph and demonstrate its ability to analyze source code written in Qiskit and OpenQASM. Our tool brings together the information from the classical and quantum world, enabling analysis across both domains. By combining all relevant information into a single detailed analysis, this powerful tool can facilitate tackling future quantum source code analysis challenges.

cs.CR↗

Representing LLVM-IR in a Code Property Graph

In the past years, a number of static application security testing tools have been proposed which make use of so-called code property graphs, a graph model which keeps rich information about the source code while enabling its user to write language-agnostic analyses. However, they suffer from several shortcomings. They work mostly on source code and exclude the analysis of third-party dependencies if they are only available as compiled binaries. Furthermore, they are limited in their analysis to whether an individual programming language is supported or not. While often support for well-established languages such as C/C++ or Java is included, languages that are still heavily evolving, such as Rust, are not considered because of the constant changes in the language design. To overcome these limitations, we extend an open source implementation of a code property graph to support LLVM-IR which can be used as output by many compilers and binary lifters. In this paper, we discuss how we address challenges that arise when mapping concepts of an intermediate representation to a CPG. At the same time, we optimize the resulting graph to be minimal and close to the representation of equivalent source code. Our evaluation indicates that existing analyses can be reused without modifications and that the performance requirements are comparable to operating on source code. This makes the approach suitable for an analysis of large-scale projects.

cs.SE↗