Automating Malware Reverse Engineering with Local LLMs, PyGhidra and Neo4j Graphs
A researcher has built an automated system that combines PyGhidra, Neo4j and a local large language model to speed up the initial analysis of malicious binaries. The project addresses the main drawbacks of sending decompiled code to cloud LLMs: leakage of indicators of compromise, possible censorship of sensitive modules, and rapid context overflow when a sample contains 100–200 functions.
Architecture and data flow
The pipeline begins with ghidra_extractor.py, which uses PyGhidra to disassemble and decompile a binary without launching the Ghidra GUI. For every function the extractor records its address, name, size, cyclomatic complexity, decompiled C pseudocode (truncated at 6000 characters with a 30-second timeout), call-graph neighbors, string references and imported API calls. Metadata such as PE format, architecture and all standard file hashes are also stored. All extracted entities are loaded into Neo4j as distinct node types: Sample, Function, String, Import, Analysis, Capability and Behavior.
Next, worker.py and mcp.py iterate over functions and send each one to a locally hosted Qwen3 model running inside LM Studio. The prompt includes both the decompiled code and the function’s position in the call graph, allowing the model to understand caller-callee relationships. The model returns structured JSON describing the function’s purpose, extracted IOCs, tags, network indicators, command-line usage and anti-analysis techniques.
aggregator.py then aggregates tags across all functions into Capability nodes that carry a strength weight reflecting how often each capability appears. builder.py combines these capabilities with the call graph to detect higher-level behavioral patterns such as file encryption combined with network activity. Finally, generator.py produces a human-readable report by querying the enriched graph.
Graph data model
Storing functions in a flat table makes it difficult to answer questions such as whether five anti-debug functions call one another. In the Neo4j model a Function node is connected to other Function nodes via CALLS edges, to String nodes via REFERENCES edges, and to Import nodes via USES edges. Capability and Behavior nodes sit above the function level and are linked through weighted relationships, enabling concise Cypher queries instead of recursive joins.
Validation on WannaCry
The pipeline was tested on a WannaCry sample obtained from MalwareBazaar. Processing 195 functions took 126 minutes on a machine with 60 GB RAM and an Nvidia 5070 Ti. The generated report identified three behavioral patterns with 100 percent confidence: File Encryption (supported by 40 functions), C2 Communication and Anti-Analysis. A publicly available YARA rule confirmed the anti-debug findings discovered by the system.
The complete source code is available in the repository Dvoranchik/MLMalwareAnalyzer. Future work will focus on refining call-graph traversal and prompt engineering to surface additional indicators.
Related articles
Cloudflare Blocks 18.2 Million DDoS Attacks in Q3 2026 Amid Shifting Attack Patterns
Cloudflare reported blocking 18.2 million network-layer DDoS attacks between July and September 2026, marking a 208% increase from the same period in 2025. The company recorded an average of roughly 8,200 attacks per hour, with 96% lasting under ten minutes and 98% staying below 1 Gbps. Large-scale attacks exceeding 1 Tbps dropped sharply from 805 in Q2 to 251 in Q3, a decline Cloudflare links to early 2026 law enforcement actions against four IoT botnets. Attack vectors shifted notably, with CLDAP reflection falling 99.5% while DNS amplification rose 215% and UDP floods grew 122%. The United States led targeted countries, followed by China and Indonesia, while media and publishing remained the most affected industry. Mirai variants accounted for 46.5% of network-layer bytes, with new families such as Dysphoria and Evooo1Bot emerging to replace dismantled botnets.
Freshko: Open-Source Rust Tool Offers Local File and URL Scanning Without Data Upload
A developer has released Freshko, a compact 400x640 pixel desktop application built in Rust that performs quick local checks on files, folders, and URLs without sending data to external services. The tool uses YARA-X rules for file scanning, follows up to eight redirects while querying Cloudflare's filtering DNS, and scores processes for potential cryptocurrency miners based on names, arguments, and launch paths. It explicitly avoids acting as a full antivirus solution, instead providing transparent results that list any skipped items or incomplete checks. Freshko runs on macOS and Windows, keeps all scan results in memory only, and disables system proxies during URL checks to prevent DNS rebinding attacks. The project includes performance benchmarks on Apple Silicon and addresses common pitfalls such as high CPU usage false positives and incomplete disk scans. Unlike VirusTotal or Cloudflare URL Scanner, Freshko performs all file analysis locally and never makes scan reports public.
Yoba Campaign Uses Signed ChatGPT and Claude Binaries for DLL Sideloading and XMRig Deployment
Researchers at Check Point Research have uncovered the Yoba malware campaign that distributes fake desktop clients for ChatGPT and Claude through GitHub repositories. The attackers bundle legitimate signed executables from OpenAI and Anthropic with a malicious DLL that gets loaded via classic sideloading. Once executed, the loader establishes persistence using the Windows Task Scheduler and retrieves additional payloads through Telegram, DNS over HTTPS, and the Catbox file hosting service. The campaign ultimately deploys the XMRig cryptominer, which pauses mining activity when user interaction is detected to avoid detection. No compromise of OpenAI or Anthropic infrastructure was found; the attackers simply repurpose the companies' signed binaries and reputation. The operation primarily targets home users and small-to-medium businesses with Windows systems.
uCreator Spyware Infiltrates Modified Telegram, WeChat and GCash Builds on Android
Security researcher Ovi has published a detailed analysis of uCreator, also known as YingGai, a commercial Android spyware platform designed for surveillance and remote app control. The malware intercepts messages, verification codes and account data directly inside legitimate applications without requiring root privileges. Infection vectors include tampered Telegram, WeChat and GCash APKs distributed through unofficial sources, as well as the Onion Box container that launches the target app inside a controlled environment. Once active, uCreator hooks into the host process, reads Telegram’s local message database through client interfaces, captures two-factor authentication passwords and hides its own session from the user. The operation is supported by cloud-based command panels and exposed GitLab repositories that revealed server-side code and development history. Compatibility problems have been noted on Android 17, and the total number of victims remains unknown.