We argue that when it comes to producing secure code with AI, the prevailing "fighting fire with fire" approach -- using probabilistic AI-based checkers or attackers to secure probabilistically generated code -- fails to address the long tail of security bugs. As a result, systems may remain exposed to zero-day vulnerabilities that can be discovered by better-resourced or more persistent adversaries.
While neurosymbolic approaches that combine LLMs with formal methods are attractive in principle, we argue that they are difficult to reconcile with the "vibe coding" workflow common in LLM-assisted development: unless the end-to-end verification pipeline is fully automated, developers are repeatedly asked to validate specifications, resolve ambiguities, and adjudicate failures, making the human-in-the-loop a likely point of weakness, compromising secure-by-construction guarantees.
In this paper we argue that stronger security guarantees can be obtained by enforcing security constraints during code generation (e.g., via constrained decoding), rather than relying solely on post-hoc detection and repair. This direction is particularly promising for diffusion-style code models, whose approach provides a natural elegant opportunity for modular, hierarchical security enforcement, allowing us to combine lower-latency generation techniques with generating secure-by-construction code.
Towards Secure Logging: Characterizing and Benchmarking Logging Code Security Issues with LLMs
York University(约克大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州));University of Waterloo(滑铁卢大学);University of Alberta(阿尔伯塔大学)
An Insight into Security Code Review with LLMs: Capabilities, Obstacles, and Influential Factors
School of Computer Science, Wuhan University, China(武汉大学计算机科学学院);School of Mathematical and Computational Sciences, Massey University(梅西大学数学与计算科学学院);School of Computing Technologies, RMIT University, Australia(皇家墨尔本理工学院计算技术学院)
Empirical Study of Code Large Language Models for Binary Security Patch Detection
National Key Laboratory for Novel Software Technology at Nanjing University(南京大学新型软件技术国家重点实验室);Harbin Institute of Technology(哈尔滨工业大学);Chinese University of Hong Kong(香港中文大学);Hong Kong University of Science and Technology(香港科学大学)
Emerging Security Challenges of Large Language Models
Télécom SudParis(巴黎高等电信学院);City University of New York(纽约城市大学);Universität Liechtenstein(列支敦士登大学);Imperial College London(伦敦帝国学院);Universität der Bundeswehr München(慕尼黑联邦国防军大学)
Towards Effective Complementary Security Analysis using Large Language Models
Data Science Group \ Web \& Software Engineering Research Group Paderborn University;Leipzig University of Applied Sciences Paderborn, Germany \ Leipzig, Germany \;Web \& Software Engineering Research Group Leipzig University of Applied Sciences Leipzig, Germany
STAF: Leveraging LLMs for Automated Attack Tree-Based Security Test Generation
Department of Systems Design Engineering, University of Waterloo, ON Canada(滑铁卢大学系统设计工程系);Smart Calibration and Virtual Testing Department, AVL List GmbH, Graz, Austria(AVL List GmbH智能校准与虚拟测试部门);Department of Computer Science, Western University, London, ON, Canada(温哥华大学计算机科学系)
Comparison of Static Application Security Testing Tools and Large Language Models for Repo-level Vulnerability Detection
Singapore Management University(新加坡管理大学);Hanoi University of Science and Technology(河内理工大学);The University of Melbourne(墨尔本大学);University of Melbourne(墨尔本大学)
LLMs Caught in the Crossfire: Malware Requests and Jailbreak Challenges
Institute of Artificial Intelligence (TeleAI), China Telecom(人工智能研究院(TeleAI),中国电信);Beihang University(北京航空航天大学);Beijing Jiaotong University(北京交通大学);Northwestern Polytechnical University(西北工业大学)
XBreaking: Understanding how LLMs security alignment can be broken
Department of Electrical, Computer;Biomedical Engineering, University of Pavia, Italy\ .;Department of Computer Applications,\ University of Science \& Technology, India\ .
A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code
Tencent(腾讯公司);Peking University(北京大学);Fudan University(复旦大学);Shanghai Jiao Tong University(上海交通大学);Tsinghua University(清华大学);Zhejiang University(浙江大学);Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);Singapore Management University(新加坡国立大学)
A Survey: Towards Privacy and Security in Mobile Large Language Models
Department of Information Technology, Kennesaw State University(肯纳邦大学信息科技系);Department of Computer Science, Georgia State University(佐治亚州立大学计算机科学系);Nexa AI;School of Computing and Artificial Intelligence, Southwest Jiaotong University(西南交通大学计算机与人工智能学院)