中文
相关论文

相关论文: Large Language Models are Edge-Case Fuzzers: Testi…

200 篇论文

Traditional database fuzzing techniques primarily focus on syntactic correctness and general SQL structures, leaving critical yet obscure DBMS features, such as system-level modes (e.g., GTID), programmatic constructs (e.g., PROCEDURE),…

Semantic understanding of programs has attracted great attention in the community. Inspired by recent successes of large language models (LLMs) in natural language understanding, tremendous progress has been made by treating programming…

机器学习 · 计算机科学 2023-06-13 Jianyu Zhao , Yuyang Rong , Yiwen Guo , Yifeng He , Hao Chen

The rapid development of large language models (LLMs) has revolutionized software testing, particularly fuzz testing, by automating the generation of diverse and effective test inputs. This advancement holds great promise for improving…

软件工程 · 计算机科学 2025-10-14 Linghan Huang , Peizhou Zhao , Huaming Chen

LLM-based (Large Language Model) fuzz driver generation is a promising research area. Unlike traditional program analysis-based method, this text-based approach is more general and capable of harnessing a variety of API usage information,…

密码学与安全 · 计算机科学 2024-07-30 Cen Zhang , Yaowen Zheng , Mingqiang Bai , Yeting Li , Wei Ma , Xiaofei Xie , Yuekang Li , Limin Sun , Yang Liu

Modern fuzzers increasingly use Large Language Models (LLMs) to generate structured inputs, but LLM-driven fuzzing is sensitive to prompt initialization and sampling variance, which can reduce exploration efficiency and lead to redundant…

密码学与安全 · 计算机科学 2026-05-05 Mario Rodríguez Béjar , B. Romera-Paredes , Jose L. Hernández-Ramos

Compilers constitute the foundational root-of-trust in software supply chains; however, their immense complexity inevitably conceals critical defects. Recent research has attempted to leverage historical bugs to design new mutation…

Deep learning (DL) has attracted wide attention and has been widely deployed in recent years. As a result, more and more research efforts have been dedicated to testing DL libraries and frameworks. However, existing work largely overlooked…

软件工程 · 计算机科学 2024-01-02 Chenyuan Yang , Yinlin Deng , Jiayi Yao , Yuxing Tu , Hanchi Li , Lingming Zhang

Internet of Things (IoT) devices offer convenience through web interfaces, web VPNs, and other web-based services, all relying on the HTTP protocol. However, these externally exposed HTTP services resent significant security risks. Although…

密码学与安全 · 计算机科学 2024-11-20 Zhe Yang , Hao Peng , Yanling Jiang , Xingwei Li , Haohua Du , Shuhai Wang , Jianwei Liu

Generation-based fuzzing produces appropriate test cases according to specifications of input grammars and semantic constraints to test systems and software. However, these specifications require significant manual effort to construct. This…

密码学与安全 · 计算机科学 2025-08-13 Chuyang Chen , Brendan Dolan-Gavitt , Zhiqiang Lin

Fuzzing is a popular dynamic program analysis technique used to find vulnerabilities in complex software. Fuzzing involves presenting a target program with crafted malicious input designed to cause crashes, buffer overflows, memory errors,…

软件工程 · 计算机科学 2017-11-15 Mohit Rajpal , William Blum , Rishabh Singh

Jailbreaking large-language models (LLMs) involves testing their robustness against adversarial prompts and evaluating their ability to withstand prompt attacks that could elicit unauthorized or malicious responses. In this paper, we…

密码学与安全 · 计算机科学 2025-06-06 Aman Goel , Xian Carrie Wu , Zhe Wang , Dmitriy Bespalov , Yanjun Qi

A fundamental problem in cybersecurity and computer science is determining whether a program is free of bugs and vulnerabilities. Fuzzing, a popular approach to discovering vulnerabilities in programs, has several advantages over…

密码学与安全 · 计算机科学 2026-01-27 Ian Hardgrove , John D. Hastings

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…

密码学与安全 · 计算机科学 2023-07-06 Tai D. Nguyen , Long H. Pham , Jun Sun

The rapidly developing deep learning (DL) techniques have been applied in software systems with various application scenarios. However, they could also pose new safety threats with potentially serious consequences, especially in…

软件工程 · 计算机科学 2024-05-14 Pin Ji , Yang Feng , Duo Wu , Lingyue Yan , Pengling Chen , Jia Liu , Zhihong Zhao

Deep Learning (DL) frameworks have served as fundamental components in DL systems over the last decade. However, bugs in DL frameworks could lead to catastrophic consequences in critical scenarios. A simple yet effective way to find bugs in…

软件工程 · 计算机科学 2026-01-21 Shaoyu Yang , Chunrong Fang , Haifeng Lin , Xiang Chen , Jia Liu , Zhenyu Chen

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…

密码学与安全 · 计算机科学 2025-04-07 Jiahao Yu , Yangguang Shao , Hanwen Miao , Junzheng Shi

Debugging is an essential skill when learning to program, yet its instruction and emphasis often vary widely across introductory courses. In the era of code-generating large language models (LLMs), the ability for students to reason about…

软件工程 · 计算机科学 2024-11-26 Victor-Alexandru Pădurean , Paul Denny , Adish Singla

Compiler correctness is crucial, as miscompilation can falsify program behaviors, leading to serious consequences. Fuzzing has been studied to uncover compiler defects. However, compiler fuzzing remains challenging: Existing arts focus on…

软件工程 · 计算机科学 2024-09-06 Chenyuan Yang , Yinlin Deng , Runyu Lu , Jiayi Yao , Jiawei Liu , Reyhaneh Jabbarvand , Lingming Zhang

Large Language Models (LLMs) have demonstrated remarkable performance in code completion. However, the training data used to develop these models often contain a significant amount of buggy code. Yet, it remains unclear to what extent these…

软件工程 · 计算机科学 2025-03-17 Liwei Guo , Sixiang Ye , Zeyu Sun , Xiang Chen , Yuxia Zhang , Bo Wang , Jie M. Zhang , Zheng Li , Yong Liu

Fuzzing has become a widely adopted technique for vulnerability discovery, yet it remains ineffective for structured-input programs due to strict syntactic constraints and limited semantic awareness. Traditional greybox fuzzers rely on…

密码学与安全 · 计算机科学 2026-04-21 Yihao Zou , Tianming Zheng , Futai Zou , Yue Wu