# Identifying Adversary Tactics and Techniques in Malware Binaries with an LLM Agent

arXiv: https://arxiv.org/abs/2602.06325 · HTML: https://mlsanity.com/paper/2602.06325/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 19 of its 53 references that are in the map.
- First posted on arXiv 6 Feb 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 19 of 19)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [TESSERACT: Eliminating Experimental Bias in Malware Classification across Space and Time](https://mlsanity.com/paper/1807.07838/) (2018)
- [Partially Observable Markov Decision Processes in Robotics: A Survey](https://mlsanity.com/paper/2209.10342/) (2022)
- [From Hard Refusals to Safe-Completions: Toward Output-Centric Safety Training](https://mlsanity.com/paper/2508.09224/) (2025)
- [RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing](https://mlsanity.com/paper/2501.18160/) (2025)
- [An Observational Investigation of Reverse Engineers' Processes](https://mlsanity.com/paper/1912.00317/) (2019)
- [LAMD: Context-driven Android Malware Detection and Classification with LLMs](https://mlsanity.com/paper/2502.13055/) (2025)
- [On Benchmarking Code LLMs for Android Malware Analysis](https://mlsanity.com/paper/2504.00694/) (2025)
- [Context2Name: A Deep Learning-Based Approach to Infer Natural Variable Names from Usage Contexts](https://mlsanity.com/paper/1809.05193/) (2018)
- [TREC: APT Tactic / Technique Recognition via Few-Shot Provenance Subgraph Learning](https://mlsanity.com/paper/2402.15147/) (2024)
- [Tactics, Techniques, and Procedures (TTPs) in Interpreted Malware: A Zero-Shot Generation with Large Language Models](https://mlsanity.com/paper/2407.08532/) (2024)
- [Automated Synthesis of Semantic Malware Signatures using Maximum Satisfiability](https://mlsanity.com/paper/1608.06254/) (2016)
- [Symbol Preference Aware Generative Models for Recovering Variable Names from Stripped Binary](https://mlsanity.com/paper/2306.02546/) (2023)
- [Large Language Models for Validating Network Protocol Parsers](https://mlsanity.com/paper/2504.13515/) (2025)
- [Is "Knowing It's Malicious Enough?" Evaluating LLMs for Fine-Grained Malware Behavior Auditing](https://mlsanity.com/paper/2509.14335/) (2025)
- [On Technique Identification and Threat-Actor Attribution using LLMs and Embedding Models](https://mlsanity.com/paper/2505.11547/) (2025)
- [Sense and Sensitivity: Examining the Influence of Semantic Recall on Long Context Code Understanding](https://mlsanity.com/paper/2505.13353/) (2025)
- [MalLoc: Toward Fine-grained Android Malicious Payload Localization via LLMs](https://mlsanity.com/paper/2508.17856/) (2025)
- [DroidTTP: Mapping Android Applications with TTP for Cyber Threat Intelligence](https://mlsanity.com/paper/2503.15866/) (2025)

## Built on by (most cited first, 2 of 2)

- [Malaika: Understanding Malware through Tri-Grounded Agentic Reasoning](https://mlsanity.com/paper/2607.09179/) (2026)
- [MARS: Malware Analysis with Rule-Based Scoring of LLM Claims](https://mlsanity.com/paper/2610.09553/) (2026)

## Abstract (arXiv)

Understanding TTPs (Tactics, Techniques, and Procedures) in malware binaries is essential for security analysis and threat intelligence, yet remains challenging in practice. Real-world malware binaries are typically stripped of symbols, contain large numbers of functions, and distribute malicious behavior across multiple code regions, making TTP attribution difficult. Recent large language models (LLMs) offer strong code understanding capabilities, but applying them directly to this task faces challenges in identifying analysis entry points, reasoning under partial observability, and misalignment with TTP-specific decision logic. We present TTPDetect, the first LLM agent for recognizing TTPs in stripped malware binaries. TTPDetect combines dense retrieval with LLM-based neural retrieval to narrow the space of analysis entry points. TTPDetect further employs a function-level analyzing agent consisting of a Context Explorer that performs on-demand, incremental context retrieval and a TTP-Specific Reasoning Guideline that achieves inference-time alignment. We build a new dataset that labels decompiled functions with TTPs across diverse malware families and platforms. TTPDetect achieves 93.25% precision and 93.81% recall on function-level TTP recognition, outperforming baselines by 10.38% and 18.78%, respectively. When evaluated on real world malware samples, TTPDetect recognizes TTPs with a precision of 87.37%. For malware with expert-written reports, TTPDetect recovers 85.7% of the documented TTPs and further discovers, on average, 10.5 previously unreported TTPs per malware.