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

• URL: http://arxiv.org/abs/2512.19758v1
• Date: Fri, 19 Dec 2025 17:03:50 GMT
• Title: Attention Distance: A Novel Metric for Directed Fuzzing with Large Language Models
• Authors: Wang Bin, Ao Yang, Kedan Li, Aofan Liu, Hui Li, Guibo Luo, Weixiang Huang, Yan Zhuang,
• Abstract summary: We introduce textbfattention distance, a novel metric that computes attention scores between code elements and reveal their intrinsic connections.<n>Compared to state-of-the-art directed fuzzers DAFL and WindRanger, our approach achieves textbf2.89$times$ and textbf7.13$times$ improvements, respectively.
• Score: 23.471848775985364
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 \textbf{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 \textbf{3.43$\times$} average increase in testing efficiency over the traditional method. Compared to state-of-the-art directed fuzzers DAFL and WindRanger, our approach achieves \textbf{2.89$\times$} and \textbf{7.13$\times$} 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/Attention\_Distance.git.

Related papers

• AlgoVeri: An Aligned Benchmark for Verified Code Generation on Classical Algorithms [54.99368693313797]
  Existing benchmarks test only individual languages/tools, so the performance numbers are not directly comparable.<n>We address this gap with AlgoVeri, a benchmark that evaluates vericoding of $77$ classical algorithms in Dafny, Verus, and Lean.
  arXiv  Detail & Related papers  (2026-02-10T06:58:26Z)
• Focus-dLLM: Accelerating Long-Context Diffusion LLM Inference via Confidence-Guided Context Focusing [18.405286688847827]
  Diffusion Large Language Models (dLLMs) deliver strong long-context processing capability in a non-autoregressive decoding paradigm.<n>We present Focus-dLLM, a novel training-free attention sparsification framework tailored for accurate and efficient long-context dLLM inference.
  arXiv  Detail & Related papers  (2026-02-02T14:36:10Z)
• Self-Supervised Visual Prompting for Cross-Domain Road Damage Detection [21.137567686181438]
  ours is a self-supervised framework that emphvisually probes target domains without labels.<n>ours consistently outperforms strong supervised, self-supervised, and adaptation baselines.<n>These results highlight self-supervised prompting as a practical direction for building scalable and adaptive visual inspection systems.
  arXiv  Detail & Related papers  (2025-11-16T01:28:45Z)
• LRANet++: Low-Rank Approximation Network for Accurate and Efficient Text Spotting [118.93173826110815]
  We propose a novel parameterized text shape method based on low-rank approximation for precise detection.<n>By exploiting the inherent shape correlation among different text contours, our method achieves consistency and compactness in shape representation.<n>We integrate the enhanced detection module with a lightweight recognition branch to form an end-to-end text spotting framework, termed LRANet++.
  arXiv  Detail & Related papers  (2025-11-08T03:08:03Z)
• Beyond Imprecise Distance Metrics: LLM-Predicted Target Call Stacks for Directed Greybox Fuzzing [11.825548125173022]
  Directed greybox fuzzing (DGF) aims to efficiently trigger bugs at specific target locations.<n>Existing DGF approaches suffer from imprecise probability calculations.<n>We propose to replace static analysis-based distance metrics with precise call stack representations.
  arXiv  Detail & Related papers  (2025-10-27T08:17:03Z)
• Prompt Guidance and Human Proximal Perception for HOT Prediction with Regional Joint Loss [9.87816757989266]
  Human-Object conTact (HOT) detection involves identifying the specific areas of the human body that are touching objects.<n>We propose a textbfP3HOT' framework, which blends textbfPrompt guidance and human textbfProximal textbfPerception.<n>Our approach achieves an improvement of textbf0.7$uparrow$, textbf2.0$uparrow$, textbf1.6$uparrow$, and textbf
  arXiv  Detail & Related papers  (2025-07-02T11:59:32Z)
• Stanceformer: Target-Aware Transformer for Stance Detection [59.69858080492586]
  Stance Detection involves discerning the stance expressed in a text towards a specific subject or target. Prior works have relied on existing transformer models that lack the capability to prioritize targets effectively. We introduce Stanceformer, a target-aware transformer model that incorporates enhanced attention towards the targets during both training and inference.
  arXiv  Detail & Related papers  (2024-10-09T17:24:28Z)
• An Empirical Study on the Distance Metric in Guiding Directed Grey-box Fuzzing [13.43238098819184]
  Directed grey-box fuzzing (DGF) aims to discover vulnerabilities in specific code areas efficiently. It remains opaque about how different distance metrics guide the fuzzing process and affect the fuzzing result in practice.
  arXiv  Detail & Related papers  (2024-09-19T12:15:54Z)
• Fréchet Denoised Distance: Enhancing Plausibility Evaluation for Generated Designs with Denoising Autoencoder [4.619979201312323]
  We propose to encode to-be-evaluated images with a Denoising Autoencoder (DAE) and measure the distribution distance in the resulting latent space. Hereby, we design a novel metric Fr'echet Denoised Distance (FDD) Our FDD can effectively detect implausible structures and is more consistent with structural inspections by human experts.
  arXiv  Detail & Related papers  (2024-03-08T14:32:01Z)
• Theoretically Achieving Continuous Representation of Oriented Bounding Boxes [64.15627958879053]
  This paper endeavors to completely solve the issue of discontinuity in Oriented Bounding Box representation. We propose a novel representation method called Continuous OBB (COBB) which can be readily integrated into existing detectors. For fairness and transparency of experiments, we have developed a modularized benchmark based on the open-source deep learning framework Jittor's detection toolbox JDet for OOD evaluation.
  arXiv  Detail & Related papers  (2024-02-29T09:27:40Z)
• Contextual information integration for stance detection via cross-attention [59.662413798388485]
  Stance detection deals with identifying an author's stance towards a target. Most existing stance detection models are limited because they do not consider relevant contextual information. We propose an approach to integrate contextual information as text.
  arXiv  Detail & Related papers  (2022-11-03T15:04:29Z)
• Cross Domain Object Detection by Target-Perceived Dual Branch Distillation [49.68119030818388]
  Cross domain object detection is a realistic and challenging task in the wild. We propose a novel Target-perceived Dual-branch Distillation (TDD) framework. Our TDD significantly outperforms the state-of-the-art methods on all the benchmarks.
  arXiv  Detail & Related papers  (2022-05-03T03:51:32Z)
• Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detection [60.88952532574564]
  This paper conducts a thorough comparison of out-of-domain intent detection methods. We evaluate multiple contextual encoders and methods, proven to be efficient, on three standard datasets for intent classification. Our main findings show that fine-tuning Transformer-based encoders on in-domain data leads to superior results.
  arXiv  Detail & Related papers  (2021-01-11T09:10:58Z)
• Structure-Consistent Weakly Supervised Salient Object Detection with Local Saliency Coherence [14.79639149658596]
  We propose a one-round end-to-end training approach for weakly supervised salient object detection via scribble annotations. Our method achieves a new state-of-the-art performance on six benchmarks.
  arXiv  Detail & Related papers  (2020-12-08T12:49:40Z)
• Dense Label Encoding for Boundary Discontinuity Free Rotation Detection [69.75559390700887]
  This paper explores a relatively less-studied methodology based on classification. We propose new techniques to push its frontier in two aspects. Experiments and visual analysis on large-scale public datasets for aerial images show the effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-11-19T05:42:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.