paper-with-me

Papers

LLAMAFUZZ: Large Language Model Enhanced Greybox Fuzzing

2024-06-11 · Hongxiang Zhang, Yuyang Rong, Yifeng He, Hao Chen

Greybox fuzzing has achieved success in revealing bugs and vulnerabilities in programs. However, randomized mutation strategies have limited the fuzzer's performance on structured data. Specialized fuzzers can handle complex structured data, but require additional efforts in grammar and suffer from low throughput. In this paper, we explore the potential of utilizing the Large Language Model to enhance greybox fuzzing for structured data. We utilize the pre-trained knowledge of LLM about data conversion and format to generate new valid inputs. We further fine-tuned it with paired mutation seeds to learn structured format and mutation strategies effectively. Our LLM-based fuzzer, LLAMAFUZZ, integrates the power of LLM to understand and mutate structured data to fuzzing. We conduct experiments on the standard bug-based benchmark Magma and a wide variety of real-world programs. LLAMAFUZZ outperforms our top competitor by 41 bugs on average. We also identified 47 unique bugs across all trials. Moreover, LLAMAFUZZ demonstrated consistent performance on both bug trigger and bug reached. Compared to AFL++, LLAMAFUZZ achieved 27.19% more branches in real-world program sets on average. We also demonstrate a case study to explain how LLMs enhance the fuzzing process in terms of code coverage.

📄 PDF Abstract BibTeX arXiv:2406.07714

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingLarge Language Modelmodelvalid

Similar Papers 제목 키워드 기반

Greybox fuzzing as a contextual bandits problem

2018-06-11 · Ketan Patil, Aditya Kanade

Greybox fuzzing is one of the most useful and effective techniques for the bug detection in large scale application programs. It uses minimal amount of instrumentation. American Fuzzy Lop (AFL) is a popular coverage base…

Multi-Armed Bandits

Augmenting Greybox Fuzzing with Generative AI

2023-06-11 · Jie Hu, Qian Zhang, Heng Yin

Real-world programs expecting structured inputs often has a format-parsing stage gating the deeper program space. Neither a mutation-based approach nor a generative approach can provide a solution that is effective and s…

Vulnerability Detection

Fuzzwise: Intelligent Initial Corpus Generation for Fuzzing

2025-12-24 · Hridya Dhulipala, Xiaokai Rong, Aashish Yadavally, Tien N. Nguyen arxiv

In mutation-based greybox fuzzing, generating high-quality input seeds for the initial corpus is essential for effective fuzzing. Rather than conducting separate phases for generating a large corpus and subsequently mini…

DeepGo: Predictive Directed Greybox Fuzzing

2025-07-29 · Peihong Lin, Pengfei Wang, Xu Zhou, Wei Xie 외 arxiv

The state-of-the-art DGF techniques redefine and optimize the fitness metric to reach the target sites precisely and quickly. However, optimizations for fitness metrics are mainly based on heuristic algorithms, which usu…

Reinforcement Learning

From CRUD to Autonomous Agents: Formal Validation and Zero-Trust Security for Semantic Gateways in AI-Native Enterprise Systems

2026-04-28 · Ignacio Peyrano arxiv

Enterprise software engineering is shifting away from deterministic CRUD/REST architectures toward AI-native systems where large language models act as cognitive orchestrators. This transition introduces a critical secur…