Deep Reinforcement Fuzzing

2018-01-14 · Konstantin Böttinger, Patrice Godefroid, Rishabh Singh

Fuzzing is the process of finding security vulnerabilities in input-processing code by repeatedly testing the code with modified inputs. In this paper, we formalize fuzzing as a reinforcement learning problem using the concept of Markov decision processes. This in turn allows us to apply state-of-the-art deep Q-learning algorithms that optimize rewards, which we define from runtime properties of the program under test. By observing the rewards caused by mutating with a specific set of actions performed on an initial program input, the fuzzing agent learns a policy that can next generate new higher-reward inputs. We have implemented this new approach, and preliminary empirical evidence shows that reinforcement fuzzing can outperform baseline random fuzzing.

📄 PDF Abstract BibTeX arXiv:1801.04589

Code (0)

등록된 구현이 없습니다.

Tasks

Q-Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…

FuzzerGym: A Competitive Framework for Fuzzing and Learning

2018-07-19 · William Drozd, Michael D. Wagner

Fuzzing is a commonly used technique designed to test software by automatically crafting program inputs. Currently, the most successful fuzzing algorithms emphasize simple, low-overhead strategies with the ability to eff…

Deep Reinforcement Learning Fault Detection OpenAI Gym reinforcement-learning+2

CovRL: Fuzzing JavaScript Engines with Coverage-Guided Reinforcement Learning for LLM-based Mutation

2024-02-19 · Jueon Eom, Seyeon Jeong, Taekyoung Kwon

Fuzzing is an effective bug-finding technique but it struggles with complex systems like JavaScript engines that demand precise grammatical input. Recently, researchers have adopted language models for context-aware muta…

reinforcement-learning Reinforcement Learning Vulnerability Detection

FuzzingRL: Reinforcement Fuzz-Testing for Revealing VLM Failures

2026-02-17 · Jiajun Xu, Jiageng Mao, Ang Qi, Weiduo Yuan 외 arxiv

Vision Language Models (VLMs) are prone to errors, and identifying where these errors occur is critical for ensuring the reliability and safety of AI systems. In this paper, we propose an approach that automatically gene…

R1-Fuzz: Specializing Language Models for Textual Fuzzing via Reinforcement Learning

2025-09-21 · Jiayi Lin, Liangcai Su, Junzhe Li, Chenxiong Qian arxiv

Fuzzing is effective for vulnerability discovery but struggles with complex targets such as compilers, interpreters, and database engines, which accept textual input that must satisfy intricate syntactic and semantic con…

Reinforcement Learning

HiFuzz: Hierarchical Reinforcement Learning for Semantic-Aware and Adaptive CPU Fuzzing

2026-07-07 · Ya Wang, Hanwei Fan, Zhenguo Liu, Xiaofeng Zhou 외 arxiv

Modern processor verification struggles to reach deep architectural states due to the inefficiencies of traditional mutation-based fuzzing. We propose HiFuzz, a novel hierarchical reinforcement learning framework that re…

Hierarchical Reinforcement Learning