We introduce a new method for extracting structured threat behaviors from threat intelligence text. Our method is based on a multi-stage ranking architecture that allows jointly optimizing for efficiency and effectiveness. Therefore, we believe this problem formulation better aligns with the real-world nature of the task considering the large number of adversary techniques and the extensive body of threat intelligence created by security analysts. Our findings show that the proposed system yields state-of-the-art performance results for this task. Results show that our method has a top-3 recall performance of 81\% in identifying the relevant technique among 193 top-level techniques. Our tests also demonstrate that our system performs significantly better (+40\%) than the widely used large language models when tested under a zero-shot setting.
EventHunter: Dynamic Clustering and Ranking of Security Events from Hacker Forum Discussions
College of Computing, Mohammed VI Polytechnic University (UM6P)(计算机学院,穆莱·伊斯梅尔理工大学(UM6P));Deloitte Morocco Cyber Center(德意志会计师事务所摩洛哥网络安全中心);Deloitte Conseil(德意志咨询)
Evaluating and Improving the Robustness of Security Attack Detectors Generated by LLMs
Samuele Pasini Universit\`a della Svizzera italiana, Switzerland Jinhan Kim Universit\`a della Svizzera italiana, Switzerland Tommaso Aiello SAP Labs France, France Rocio Cabrera Lozoya SAP Labs France, France Antonino Sabetta SAP Labs France, France Paolo Tonella Universit\`a della Svizzera italiana, Switzerland
Incident-Data Robustness Analysis of the OWASP Top 10 for LLM Applications (2026): How a Community-Expert Ranking Holds Up Against a Large-Scale LLM Incident Corpus
OWASP GenAI Security Project — Top 10 for LLM Applications(OWASP GenAI安全项目——LLM应用十大项目)
RealAI(瑞莱智慧);Tsinghua University(清华大学);Beijing Institute of Technology(北京理工大学);Shanghai Jiao Tong University(上海交通大学);China Nanhu Academy of Electronics and Information Technology(中国电子科技南湖研究院);Xi’an Jiaotong University(西安交通大学);Tencent YouTu Lab(腾讯优图实验室);China Construction Bank Fintech(中国建设银行金融科技公司);RippleInfo(涟漪信息科技)