English
Related papers

Related papers: Augmenting Greybox Fuzzing with Generative AI

200 papers

Large language models (LLMs), such as ChatGPT, are able to generate human-like, fluent responses for many downstream tasks, e.g., task-oriented dialog and question answering. However, applying LLMs to real-world, mission-critical…

Computation and Language · Computer Science 2023-03-10 Baolin Peng , Michel Galley , Pengcheng He , Hao Cheng , Yujia Xie , Yu Hu , Qiuyuan Huang , Lars Liden , Zhou Yu , Weizhu Chen , Jianfeng Gao

Tool-augmented LLM agents increasingly rely on multi-step, multi-tool workflows to complete real tasks. This design expands the attack surface, because data produced by one tool can be persisted and later reused as input to another tool,…

Software Engineering · Computer Science 2026-03-16 Jiangrong Wu , Zitong Yao , Yuhong Nan , Zibin Zheng

Fuzzing has emerged as a powerful technique for finding security bugs in complicated real-world applications. American fuzzy lop (AFL), a leading fuzzing tool, has demonstrated its powerful bug finding ability through a vast number of…

Cryptography and Security · Computer Science 2023-07-06 Tai D. Nguyen , Long H. Pham , Jun Sun

Automatic test generation typically aims to generate inputs that explore new paths in the program under test in order to find bugs. Existing work has, therefore, focused on guiding the exploration toward program parts that are more likely…

Software Engineering · Computer Science 2019-05-20 Valentin Wüstholz , Maria Christakis

Greybox fuzzing is the de-facto standard to discover bugs during development. Fuzzers execute many inputs to maximize the amount of reached code. Recently, Directed Greybox Fuzzers (DGFs) propose an alternative strategy that goes beyond…

Cryptography and Security · Computer Science 2022-07-28 Han Zheng , Jiayuan Zhang , Yuhang Huang , Zezhong Ren , He Wang , Chunjie Cao , Yuqing Zhang , Flavio Toffalini , Mathias Payer

Large Language Models (LLMs) have gained widespread use in various applications due to their powerful capability to generate human-like text. However, prompt injection attacks, which involve overwriting a model's original instructions with…

Cryptography and Security · Computer Science 2025-04-07 Jiahao Yu , Yangguang Shao , Hanwen Miao , Junzheng Shi

Software model checking is a verification technique which is widely used for checking temporal properties of software systems. Even though it is a property verification technique, its common usage in practice is in "bug finding", that is,…

Software Engineering · Computer Science 2022-04-20 Ruijie Meng , Zhen Dong , Jialin Li , Ivan Beschastnikh , Abhik Roychoudhury

Testing ultra-large microservices-based FinTech systems presents significant challenges, including restricted access to production environments, complex dependencies, and stringent security constraints. We propose SandBoxFuzz, a scalable…

Software Engineering · Computer Science 2025-04-29 Jiazhao Yu , Yanlun Tu , Zhanlei Zhang , Tiehua Zhang , Cheng Xu , Weigang Wu , Hong Jin Kang , Xi Zheng

Coverage-based greybox fuzzing (CGF) has been approved to be effective in finding security vulnerabilities. Seed scheduling, the process of selecting an input as the seed from the seed pool for the next fuzzing iteration, plays a central…

Software Engineering · Computer Science 2022-06-16 Yiru Zhao , Xiaoke Wang , Lei Zhao , Yueqiang Cheng , Heng Yin

Generative AI offers a simple, prompt-based alternative to fine-tuning smaller BERT-style LLMs for text classification tasks. This promises to eliminate the need for manually labeled training data and task-specific model training. However,…

Computation and Language · Computer Science 2024-08-19 Martin Juan José Bucher , Marco Martini

We improve the performance of the American Fuzzy Lop (AFL) fuzz testing framework by using Generative Adversarial Network (GAN) models to reinitialize the system with novel seed files. We assess performance based on the temporal rate at…

Artificial Intelligence · Computer Science 2017-11-09 Nicole Nichols , Mark Raugas , Robert Jasper , Nathan Hilliard

Large Language Models (LLM) are increasingly integrated into everyday interactions, serving not only as information assistants but also as emotional companions. Even in the absence of explicit toxicity, repeated emotional reinforcement or…

Computation and Language · Computer Science 2026-01-23 Jihyung Park , Saleh Afroogh , David Atkinson , Junfeng Jiao

Ensuring the correctness of compiler optimizations is critical, but existing fuzzers struggle to test optimizations effectively. First, most fuzzers use optimization pipelines (heuristics-based, fixed sequences of passes) as their harness.…

Software Engineering · Computer Science 2025-12-05 Zitong Zhou , Ben Limpanukorn , Hong Jin Kang , Jiyuan Wang , Yaoxuan Wu , Akos Kiss , Renata Hodovan , Miryung Kim

Coverage-guided Greybox Fuzzing (CGF) is one of the most successful and widely-used techniques for bug hunting. Two major approaches are adopted to optimize CGF: (i) to reduce search space of inputs by inferring relationships between input…

Cryptography and Security · Computer Science 2022-01-13 Kunpeng Zhang , Xi Xiao , Xiaogang Zhu , Ruoxi Sun , Minhui Xue , Sheng Wen

As with any fuzzer, directing Generator-Based Fuzzers (GBF) to reach particular code targets can increase the fuzzer's effectiveness. In previous work, coverage-guided fuzzers used a mix of static analysis, taint analysis, and…

Software Engineering · Computer Science 2026-01-21 Soha Hussein , Stephen McCamant , Mike Whalen

Fuzzing is highly effective in detecting bugs due to the key contribution of randomness. However, randomness significantly reduces the efficiency of fuzzing, causing it to cost days or weeks to expose bugs. Even though directed fuzzing…

Software Engineering · Computer Science 2025-07-31 Xiaotao Feng , Xiaogang Zhu , Kun Hu , Jincheng Wang , Yingjie Cao , Guang Gong , Jianfeng Pan

Fuzzing technologies have evolved at a fast pace in recent years, revealing bugs in programs with ever increasing depth and speed. Applications working with complex formats are however more difficult to take on, as inputs need to meet…

Cryptography and Security · Computer Science 2020-08-13 Andrea Fioraldi , Daniele Cono D'Elia , Emilio Coppa

Fuzzing continues to be the most effective method for identifying security vulnerabilities in software. In the context of fuzz testing, the fuzzer supplies varied inputs to fuzz targets, which are designed to comprehensively exercise…

Software Engineering · Computer Science 2026-01-21 Chi Thien Tran

Existing LLM-based compiler fuzzers often produce syntactically or semantically invalid test programs, limiting their effectiveness in exercising compiler optimizations and backend components. We introduce ReFuzzer, a framework for refining…

Software Engineering · Computer Science 2025-09-02 Iti Shree , Karine Even-Mendoza , Tomasz Radzik

Fuzzing network servers is a technical challenge, since the behavior of the target server depends on its state over a sequence of multiple messages. Existing solutions are costly and difficult to use, as they rely on manually-customized…

Cryptography and Security · Computer Science 2022-10-05 Roberto Natella