# Attention Distance: A Novel Metric for Directed Fuzzing with Large Language Models

arXiv: https://arxiv.org/abs/2512.19758 · HTML: https://mlsanity.com/paper/2512.19758/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 42 references that are in the map.
- First posted on arXiv 19 Dec 2025.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [InCoder: A Generative Model for Code Infilling and Synthesis](https://mlsanity.com/paper/2204.05999/) (2022)
- [CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X](https://mlsanity.com/paper/2303.17568/) (2023)
- [Large Language Models for Code: Security Hardening and Adversarial Testing](https://mlsanity.com/paper/2302.05319/) (2023)
- [Large Language Models Meet NL2Code: A Survey](https://mlsanity.com/paper/2212.09420/) (2022)
- [Improving Automatic Source Code Summarization via Deep Reinforcement Learning](https://mlsanity.com/paper/1811.07234/) (2018)
- [Large Language Models for Compiler Optimization](https://mlsanity.com/paper/2309.07062/) (2023)
- [FairFuzz: Targeting Rare Branches to Rapidly Increase Greybox Fuzz Testing Coverage](https://mlsanity.com/paper/1709.07101/) (2017)
- [DriveFuzz: Discovering Autonomous Driving Bugs through Driving Quality-Guided Fuzzing](https://mlsanity.com/paper/2211.01829/) (2022)
- [Angora: Efficient Fuzzing by Principled Search](https://mlsanity.com/paper/1803.01307/) (2018)
- [Enhancing Large Language Models for Secure Code Generation: A Dataset-driven Study on Vulnerability Mitigation](https://mlsanity.com/paper/2310.16263/) (2023)
- [Enhanced Automated Code Vulnerability Repair using Large Language Models](https://mlsanity.com/paper/2401.03741/) (2024)
- [MC2: Rigorous and Efficient Directed Greybox Fuzzing](https://mlsanity.com/paper/2208.14530/) (2022)
- [State Selection Algorithms and Their Impact on The Performance of Stateful Network Protocol Fuzzing](https://mlsanity.com/paper/2112.15498/) (2021)
- [SyzTrust: State-aware Fuzzing on Trusted OS Designed for IoT Devices](https://mlsanity.com/paper/2309.14742/) (2023)

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

- [Execution-State-Aware LLM Reasoning for Automated Proof-of-Vulnerability Generation](https://mlsanity.com/paper/2602.13574/) (2026)
- [SyzHarness: Patch-Based Kernel Bug Reproduction with LLM-Synthesized Fuzzing Harnesses](https://mlsanity.com/paper/2609.23889/) (2026)

## Abstract (arXiv)

In the domain of software security testing, Directed Grey-Box Fuzzing (DGF) has garnered widespread attention for its efficient target localization and excellent detection performance. However, existing approaches measure only the physical distance between seed execution paths and target locations, overlooking logical relationships among code segments. This omission can yield redundant or misleading guidance in complex binaries, weakening DGF's real-world effectiveness. To address this, we introduce attention distance, a novel metric that leverages a large language model's contextual analysis to compute attention scores between code elements and reveal their intrinsic connections. Under the same AFLGo configuration -- without altering any fuzzing components other than the distance metric -- replacing physical distances with attention distances across 38 real vulnerability reproduction experiments delivers a 3.43× average increase in testing efficiency over the traditional method. Compared to state-of-the-art directed fuzzers DAFL and WindRanger, our approach achieves 2.89× and 7.13× improvements, respectively. To further validate the generalizability of attention distance, we integrate it into DAFL and WindRanger, where it also consistently enhances their original performance. All related code and datasets are publicly available at https://github.com/TheBinKing/AttentionDistance.git.