Large Language Models Are Zero-Shot Fuzzers: Fuzzing Deep-Learning Libraries via Large Language Models

计算机科学 模糊测试 程序设计语言 Python(编程语言) 人工智能 语法 语义学(计算机科学) 编码(集合论) 自然语言处理 软件 集合(抽象数据类型)
作者
Yinlin Deng,Chunqiu Steven Xia,Haoran Peng,Chenyuan Yang,Lingming Zhang
标识
DOI:10.1145/3597926.3598067
摘要

Deep Learning (DL) systems have received exponential growth in popularity and have become ubiquitous in our everyday life. Such systems are built on top of popular DL libraries, e.g., TensorFlow and PyTorch which provide APIs as building blocks for DL systems. Detecting bugs in these DL libraries is critical for almost all downstream DL systems in ensuring effectiveness/safety for end users. Meanwhile, traditional fuzzing techniques can be hardly effective for such a challenging domain since the input DL programs need to satisfy both the input language (e.g., Python) syntax/semantics and the DL API input/shape constraints for tensor computations. To address these limitations, we propose TitanFuzz – the first approach to directly leveraging Large Language Models (LLMs) to generate input programs for fuzzing DL libraries. LLMs are titanic models trained on billions of code snippets and can autoregressively generate human-like code snippets. Our key insight is that modern LLMs can also include numerous code snippets invoking DL library APIs in their training corpora, and thus can implicitly learn both language syntax/semantics and intricate DL API constraints for valid DL program generation. More specifically, we use both generative and infilling LLMs (e.g., Codex/InCoder) to generate and mutate valid/diverse input DL programs for fuzzing. Our experimental results demonstrate that TitanFuzz can achieve 30.38%/50.84% higher code coverage than state-of-the-art fuzzers on TensorFlow/PyTorch. Furthermore, TitanFuzz is able to detect 65 bugs, with 44 already confirmed as previously unknown bugs. This paper demonstrates that modern titanic LLMs can be leveraged to directly perform both generation-based and mutation-based fuzzing studied for decades, while being fully automated, generalizable, and applicable to domains challenging for traditional approaches (such as DL systems). We hope TitanFuzz can stimulate more work in this promising direction of LLMs for fuzzing.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
Hodlumm发布了新的文献求助10
2秒前
有趣的灵魂完成签到,获得积分10
5秒前
今后应助shen采纳,获得10
6秒前
桐桐应助科研通管家采纳,获得10
7秒前
爆米花应助科研通管家采纳,获得10
7秒前
李健应助科研通管家采纳,获得10
8秒前
Akim应助科研通管家采纳,获得10
8秒前
8秒前
星辰大海应助科研通管家采纳,获得10
8秒前
烟花应助科研通管家采纳,获得10
8秒前
科研通AI2S应助科研通管家采纳,获得10
8秒前
Ava应助科研通管家采纳,获得10
8秒前
Jasper应助科研通管家采纳,获得10
8秒前
Hello应助科研通管家采纳,获得10
8秒前
SciGPT应助科研通管家采纳,获得10
9秒前
9秒前
9秒前
9秒前
10秒前
lennon完成签到,获得积分10
10秒前
量子星尘发布了新的文献求助10
11秒前
zjrh完成签到,获得积分10
12秒前
小李子发布了新的文献求助10
13秒前
春花发布了新的文献求助10
14秒前
刘星完成签到 ,获得积分10
15秒前
小蘑菇应助saisyo采纳,获得10
15秒前
16秒前
单薄碧灵完成签到 ,获得积分10
17秒前
CodeCraft应助mashichuang采纳,获得10
19秒前
yyyyyyyyyyyiiii完成签到 ,获得积分10
19秒前
深海敢敢发布了新的文献求助10
22秒前
小李子完成签到,获得积分10
22秒前
qingkong完成签到 ,获得积分10
22秒前
23秒前
24秒前
Lsc发布了新的文献求助10
25秒前
26秒前
无花果应助研友_QLXYgn采纳,获得10
27秒前
30秒前
31秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 700
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3976418
求助须知:如何正确求助?哪些是违规求助? 3520512
关于积分的说明 11203586
捐赠科研通 3257127
什么是DOI,文献DOI怎么找? 1798594
邀请新用户注册赠送积分活动 877804
科研通“疑难数据库(出版商)”最低求助积分说明 806523