While Large Language Models (LLMs) excel in code generation, they remain prone to replicating subtle yet critical vulnerabilities endemic to their training data. Current alignment techniques, such as Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), typically apply coarse-grained optimization at the sequence level. This approach often fails to address the localized nature of security flaws, where a single incorrect token choice can compromise an entire program. To bridge this gap, we introduce Tree-like Self-Play (TSP), a framework that reframes secure code generation as a fine-grained sequential decision process. Unlike standard methods that blindly maximize likelihood, TSP constructs a decision tree where the model explores branching trajectories--generating both secure "golden paths" and vulnerable variants. By treating code generation as a self-play game, the model learns to strictly discriminate against its own localized errors. This provides a dense, on-policy learning signal that forces self-correction precisely at the critical decision nodes where vulnerabilities typically emerge. Our experiments demonstrate that TSP fundamentally enhances model reliability. In Python security benchmarks, TSP boosts CodeLlama-7B's pass rate (SPR@1) to 75.8%, significantly outperforming SFT (57.0%) and unstructured self-play baselines. Crucially, TSP induces robust out-of-distribution generalization: the model not only reduces vulnerabilities in unseen categories (CWEs) by 24.5% but also successfully transfers security principles learned from C/C++ to diverse languages, including Python, Go, and JavaScript. This suggests that TSP does not merely memorize patches, but internalizes abstract, language-agnostic security logic.
LLMs can Find Mathematical Reasoning Mistakes by Pedagogical Chain-of-Thought
Shanghai Business School（上海商学院）；Learnable.AI Inc.（Learnable.AI公司）；Centre for Frontier AI Research, A*STAR（前沿人工智能研究中心，A*STAR）；Institute of High-Performance Computing, A*STAR（高性能计算研究所，A*STAR）；The Hong Kong Polytechnic University（香港理工大学）；Microsoft Research Asia（微软亚洲研究院）
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）
Pathway to Secure and Trustworthy ZSM for LLMs: Attacks, Defense, and Opportunities
School of Computing, Dublin City University（都柏林城市大学计算机学院）；Institute of Business Administration, University of Sindh（信德大学工商管理学院）；Munster Technological University（芒斯特理工大学）；Centre Tecnològic de Telecomunicacions de Catalunya (CTTC)（加泰罗尼亚电信技术中心）
Nanyang Technological University（南洋理工大学）；AI Singapore（新加坡人工智能研究院）；Hangzhou Innovation Institute, Beihang University（北京航空航天大学杭州创新研究院）；School of Computer Science and Technology, Anhui University（安徽大学计算机科学与技术学院）；Qiyuan laboratory（启元实验室）；IHPC, Agency for Science, Technology and Research, Singapore（新加坡科技研究局高性能计算研究院）；CoAI Group, Tsinghua University（清华大学CoAI组）；Institute of High Performance Computing, Agency for Science, Technology and Research (A*STAR), Singapore（新加坡科技研究局高性能计算研究院）
SecureFalcon: Are We There Yet in Automated Software Vulnerability Detection with LLMs?
Guelma University（盖勒马大学）；Technology Innovation Institute（技术创新研究院）；Khalifa University of Science and Technology（哈利法科技大学）；University of Manchester（曼彻斯特大学）
CodeBC: A More Secure Large Language Model for Smart Contract Code Generation in Blockchain
State Key Laboratory of Complex & Critical Software Environment, Beihang University（复杂与关键软件环境国家重点实验室，北京航空航天大学）；School of Artificial Intelligence, Beihang University（人工智能学院，北京航空航天大学）；Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing（未来区块链与隐私计算北京先进创新中心）；Beijing Academy of Blockchain and Edge Computing, BABEC（区块链与边缘计算北京研究院，BABEC）
The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs
University of Cambridge（剑桥大学）；Institute for AI, University of Stuttgart（斯图加特大学人工智能研究所）；Max Planck Institute for Intelligent Systems（智能系统马克斯·普朗克研究所）；ELLIS Institute Tübingen（图宾根ELLIS研究所）；University of Southampton（南安普顿大学）；Tübingen AI Center（图宾根人工智能中心）
How Well Do Large Language Models Serve as End-to-End Secure Code Agents for Python?
School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）；State Key Laboratory of Software Development Environment（软件开发环境国家重点实验室）；Zhongguancun Laboratory（中关村实验室）；Tsinghua University（清华大学）
LLMs meet Federated Learning for Scalable and Secure IoT Management
School of Computer Science and Technology, Algoma University（计算机科学与技术学院，阿尔戈马大学）；School of Electrical Engineering and Computer Science, University of Ottawa（电气工程与计算机科学学院，渥太华大学）
