English
Related papers

Related papers: Large Language Models are Edge-Case Fuzzers: Testi…

200 papers

Robustness is a key concern for Rust library development because Rust promises no risks of undefined behaviors if developers use safe APIs only. Fuzzing is a practical approach for examining the robustness of programs. However, existing…

Software Engineering · Computer Science 2021-10-25 Jianfeng Jiang , Hui Xu , Yangfan Zhou

The remarkable capability of large language models (LLMs) in generating high-quality code has drawn increasing attention in the software testing community. However, existing code LLMs often demonstrate unsatisfactory capabilities in…

Software Engineering · Computer Science 2024-02-07 Yifeng He , Jiabo Huang , Yuyang Rong , Yiwen Guo , Ethan Wang , Hao Chen

Fuzzing is a widely used software security testing technique that is designed to identify vulnerabilities in systems by providing invalid or unexpected input. Continuous fuzzing systems like OSS-FUZZ have been successful in finding security…

Cryptography and Security · Computer Science 2023-07-04 Chaitanya Rahalkar

The emergence of Large Language Models (LLMs), including ChatGPT, is having a significant impact on a wide range of fields. While LLMs have been extensively researched for tasks such as code generation and text synthesis, their application…

Cryptography and Security · Computer Science 2025-02-17 Takashi Koide , Naoki Fukushi , Hiroki Nakano , Daiki Chiba

In NLP, reusing pre-trained models instead of training from scratch has gained popularity; however, NLP models are mostly black boxes, very large, and often require significant resources. To ease, models trained with large corpora are made…

Software Engineering · Computer Science 2022-12-02 Rangeet Pan , Sumon Biswas , Mohna Chakraborty , Breno Dantas Cruz , Hridesh Rajan

Large Language Models (LLMs) are advanced Artificial Intelligence (AI) systems that have undergone extensive training using large datasets in order to understand and produce language that closely resembles that of humans. These models have…

Software Engineering · Computer Science 2023-08-10 Alessio Buscemi

Large Language Models (LLMs), with their remarkable ability to tackle challenging and unseen reasoning problems, hold immense potential for tabular learning, that is vital for many real-world applications. In this paper, we propose a novel…

Machine Learning · Computer Science 2024-05-07 Sungwon Han , Jinsung Yoon , Sercan O Arik , Tomas Pfister

GPU memory errors are a critical threat to deep learning (DL) frameworks, leading to crashes or even security issues. We introduce GPU-Fuzz, a fuzzer locating these issues efficiently by modeling operator parameters as formal constraints.…

Cryptography and Security · Computer Science 2026-03-03 Zihao Li , Hongyi Lu , Yanan Guo , Zhenkai Zhang , Shuai Wang , Fengwei Zhang

GPUs play an increasingly important role in modern software. However, the heterogeneous host-device execution model and expanding software stacks make GPU programs prone to memory-safety and concurrency bugs that evade static analysis.…

Cryptography and Security · Computer Science 2026-03-16 Mohamed Tarek Ibn ziad , Christos Kozyrakis

Large language models (LLMs), such as ChatGPT, have rapidly penetrated into people's work and daily lives over the past few years, due to their extraordinary conversational skills and intelligence. ChatGPT has become the fastest-growing…

Computation and Language · Computer Science 2024-09-04 Wenxuan Wang

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

Various deep learning-based approaches utilizing pre-trained language models (PLMs) have been proposed for automated vulnerability detection. With recent advancements in large language models (LLMs), several studies have begun exploring…

Software Engineering · Computer Science 2026-03-11 Honglin Shu , Michael Fu , Junji Yu , Dong Wang , Chakkrit Tantithamthavorn , Junjie Chen , Yasutaka Kamei

Large language models (LLMs) have demonstrated notable proficiency in code generation, with numerous prior studies showing their promising capabilities in various development scenarios. However, these studies mainly provide evaluations in…

Software Engineering · Computer Science 2024-03-19 Kailun Jin , Chung-Yu Wang , Hung Viet Pham , Hadi Hemmati

We present a coverage-guided testing algorithm for distributed systems implementations. Our main innovation is the use of an abstract formal model of the system that is used to define coverage. Such abstract models are frequently developed…

Software Engineering · Computer Science 2025-09-03 Ege Berkay Gulcan , Burcu Kulahcioglu Ozkan , Rupak Majumdar , Srinidhi Nagendra

Large language models (LLMs) have achieved impressive performance on code generation. However, for complex programming tasks, generating the correct solution in one go becomes challenging, thus some prior works have designed program repair…

Computation and Language · Computer Science 2023-10-06 Xinyun Chen , Maxwell Lin , Nathanael Schärli , Denny Zhou

MLIR (Multi-Level Intermediate Representation) has rapidly become a foundational technology for modern compiler frameworks, enabling extensibility across diverse domains. However, ensuring the correctness and robustness of MLIR itself…

Software Engineering · Computer Science 2025-10-10 Zeyu Sun , Jingjing Liang , Weiyi Wang , Chenyao Suo , Junjie Chen , Fanjiang Xu

Generative Models (GMs), particularly Large Language Models (LLMs), have garnered significant attention in machine learning and artificial intelligence for their ability to generate new data by learning the statistical properties of…

Artificial Intelligence · Computer Science 2025-12-03 Hailong Yang , Zhaohong Deng , Wei Zhang , Zhuangzhuang Zhao , Guanjin Wang , Kup-sze Choi

Static analysis is a widely used technique in software engineering for identifying and mitigating bugs. However, a significant hurdle lies in achieving a delicate balance between precision and scalability. Large Language Models (LLMs) offer…

Software Engineering · Computer Science 2023-11-17 Haonan Li , Yu Hao , Yizhuo Zhai , Zhiyun Qian

The Language Server Protocol (LSP) has revolutionized the integration of code intelligence in modern software development. There are approximately 300 LSP server implementations for various languages and 50 editors offering LSP integration.…

Software Engineering · Computer Science 2026-01-29 Hengcheng Zhu , Songqiang Chen , Valerio Terragni , Lili Wei , Yepang Liu , Jiarong Wu , Shing-Chi Cheung

Security vulnerabilities are increasingly prevalent in modern software and they are widely consequential to our society. Various approaches to defending against these vulnerabilities have been proposed, among which those leveraging deep…

Cryptography and Security · Computer Science 2024-02-28 Yu Nong , Mohammed Aldeen , Long Cheng , Hongxin Hu , Feng Chen , Haipeng Cai