基于短信的钓鱼攻击(smishing)已显著增加,但训练有效的设备端检测器需要标记的威胁数据,这些数据很快会过时。为了解决这个问题,我们提出了代理知识蒸馏,其中一个强大的LLM充当自主教师,微调一个较小的学生SLM,可用于安全任务而无需人工干预。教师LLM自主生成合成数据,并迭代优化较小的设备端学生模型,直到性能达到平台期。我们在此教师角色上比较了四种LLM(Claude Opus 4.5、GPT 5.2 Codex、Gemini 3 Pro和DeepSeek V3.2)在短信垃圾/钓鱼检测中的表现,与两种学生SLM(Qwen2.5-0.5B和SmolLM2-135M)。我们的结果表明,性能在很大程度上取决于教师LLM的选择,最佳配置实现了94.31%的准确率和96.25%的召回率。我们还与一个直接偏好优化(DPO)基线进行了比较,该基线使用相同的合成知识和LoRA设置,但没有迭代反馈或针对性优化;代理知识蒸馏显著优于它(例如,86-94% vs 50-80%准确率),表明闭环反馈和针对性优化是关键。这些发现表明,代理知识蒸馏可以快速产生有效的安全分类器用于边缘部署,但结果在很大程度上取决于所使用的教师LLM。
英文摘要:
SMS-based phishing (smishing) attacks have surged, yet training effective on-device detectors requires labelled threat data that quickly becomes outdated. To deal with this issue, we present Agentic Knowledge Distillation, which consists of a powerful LLM acts as an autonomous teacher that fine-tunes a smaller student SLM, deployable for security tasks without human intervention. The teacher LLM autonomously generates synthetic data and iteratively refines a smaller on-device student model until performance plateaus. We compare four LLMs in this teacher role (Claude Opus 4.5, GPT 5.2 Codex, Gemini 3 Pro, and DeepSeek V3.2) on SMS spam/smishing detection with two student SLMs (Qwen2.5-0.5B and SmolLM2-135M). Our results show that performance varies substantially depending on the teacher LLM, with the best configuration achieving 94.31% accuracy and 96.25% recall. We also compare against a Direct Preference Optimisation (DPO) baseline that uses the same synthetic knowledge and LoRA setup but without iterative feedback or targeted refinement; agentic knowledge distillation substantially outperforms it (e.g. 86-94% vs 50-80% accuracy), showing that closed-loop feedback and targeted refinement are critical. These findings demonstrate that agentic knowledge distillation can rapidly yield effective security classifiers for edge deployment, but outcomes depend strongly on which teacher LLM is used.
New Threats to SMS-Assisted Mobile Internet Services from 4G LTE: Lessons Learnt from Distributed Mobile-Initiated Attacks towards Facebook and Other Services
A Security Analysis of Long-Horizon Agentic AI Systems: Threats, Evaluation, and Framework Development
Department of Computer Science, College of Computers and Information Technology, Taif University, KSA (Summer 2026)(计算机科学系,计算机与信息科技学院,泰夫大学,沙特阿拉伯(2026年夏季))
ASTRIDE: A Security Threat Modeling Platform for Agentic-AI Applications
Old Dominion University(老奥布里恩大学);Accenture Technology Labs(埃森哲技术实验室);Florida International University(佛罗里达国际大学);Nanyang Technological University(南洋理工大学);University of Colombo(科伦坡大学)
Agentic Artificial Intelligence for Ethical Cybersecurity in Uganda: A Reinforcement Learning Framework for Threat Detection in Resource-Constrained Environments
Department of Computing, Faculty of Science and Technology, Kampala International University(坎帕拉国际大学科学与技术学院计算系);Department of Electrical, Telecommunication, and Computer Engineering, Kampala International University(坎帕拉国际大学电气、电信和计算机工程系)
MATRA: Modeling the Attack Surface of Agentic AI Systems -- OpenClaw Case Study
DistriNet, KU Leuven(DistriNet,根特大学);IBM Research(IBM研究院);CISPA Helmholtz Center for Information Security(CISPA海德堡信息安全中心);Imperial College London(伦敦帝国理工学院);A*STAR Institute for Infocomm Research(A*STAR信息与通信研究机构)
Machine Learning Driven Smishing Detection Framework for Mobile Security
CSIRO’s Data61(澳大利亚联邦科学与工业研究组织Data61);National Institute of Technology, Kurukshetra(库鲁克谢特拉国家理工学院);University of Adelaide(阿德莱德大学);PGIMS, Haryana, India(印度哈里亚纳邦PGIMS)
The State Key Laboratory of Blockchain and Data Security, Zhejiang University(浙江大学区块链与数据安全国家重点实验室);State Key Laboratory of Internet Architecture, Tsinghua University(清华大学互联网架构国家重点实验室);Huazhong University of Science and Technology(华中科技大学);Shanghai AI Laboratory(上海人工智能实验室);East China Normal University(华东师范大学)
VirtualCrime: Evaluating the Criminal Potential and Agentic Behaviors of Large Language Models via Sandbox Simulation
Shanghai Qi Zhi Institute(上海智源研究院);Institute for Interdisciplinary Information Sciences, Tsinghua University(清华大学交叉信息研究院);Xiongan AI Institute(雄安人工智能研究院);Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China(中国科学院信息工程研究所);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳))
A Finger on the Scale: Covert Policy Steering through Agentic Skills
School of Big Data & Software Engineering, Chongqing University(重庆大学大数据与软件工程学院);College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院)
Uncovering Security Threats and Architecting Defenses in Autonomous Agents: A Case Study of OpenClaw
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);Zhongguancun Laboratory(中关村实验室);Hefei Comprehensive National Science Center Institute of Dataspace(合肥综合性国家科学中心数据空间研究院)