The paper introduces a Cost-Aware Hierarchical Multi-Agent System (HMAS) for ransomware detection and family attribution that adaptively selects analysis modalities to balance accuracy and computational cost. Static analysis is used first, with dynamic and memory modalities added only when confidence is low or specialist agents disagree, guided by a cost model. Experiments show HMAS achieves high accuracy (96.57% binary detection, 0.90 macro‑F1 attribution) while reducing analysis cost by 43.97% and latency, with 56.05% of cases resolved using static evidence alone.
By Mubashar Iqbal, Asifullah Khan
arXiv:2607. 04292v1 Announce Type: new Abstract: Ransomware has evolved into a complex, adaptive, and fast-moving adversary category in which static signatures and monolithic classifiers fail to generalise under concept drift, evasion, and behavioural polymorphism.
By Henry Kabuye, Biju Issac, Jeyamohan Neera
arXiv:2607. 20216v1 Announce Type: cross Abstract: Malware analysis demands rapid interpretation of complex detonation reports spanning filesystem, network, and process behaviours.
By Adel ElZemity, Shujun Li, Budi Arief
arXiv:2603. 13384v2 Announce Type: replace-cross Abstract: Software vulnerabilities often depend on cross-file data flow, build options, framework conventions, and runtime guards, so isolated function classifiers produce fragile and poorly calibrated warnings.
By Renwei Meng, Haoyi Wu, Jingming Wang
arXiv:2509. 14335v2 Announce Type: replace-cross Abstract: Automated malware classifiers achieve strong detection performance, but auditing requires more than flagging a sample: analysts must explain malicious behaviors and justify them with code evidence.
By Xinran Zheng, Xingzhi Qian, Yiling He, Shuo Yang, Lorenzo Cavallaro
arXiv:2607. 26791v1 Announce Type: cross Abstract: Large Language Model (LLM) agents are increasingly adopted in real-world security operations with access to host artifacts and command-line interfaces (CLIs), making it critical to thoroughly assess their security capabilities.
By Lehan Wang, Boli Chen, Ruixue Ding, Pengjun Xie, Jinwei Huang, Zhendong Liu, Shuo Wang, Tao Lei, Xin Ouyang, Xiaomeng Li
arXiv:2606. 03453v1 Announce Type: cross Abstract: Vulnerability disclosure volumes now far exceed organizational assessment capacity, yet three adjacent research communities (proof-of-concept generation, vulnerability prioritization, and detection rule engineering) operate largely in isolation.
By Farooq Shaikh
The paper investigates an agentic framework for open‑world fake image detection that combines specialist detectors with per‑detector triage, prompting, and conflict‑aware evidence arbitration. Experiments across six configurations and three multimodal large language model backbones reveal that naive detector fusion yields high false‑positive rates, while triage and prompting consistently filter unreliable evidence. The most significant improvement comes from the reasoning component: a stronger judge markedly outperforms a weaker one, especially under distribution shift, and overall manipulation recall is nearly saturated, highlighting that the key challenge lies in calibrating trust and arbitrating conflicting forensic evidence rather than detecting manipulations themselves.
By Xianlong Li (IMT School for Advanced Studies Lucca, Italy), Pietro Bongini (University of Siena, Italy), Niccol\'o Pancino (University of Siena, Italy), Marco Blanchini (IMT School for Advanced Studies Lucca, Italy), Benedetta Tondi (University of Siena, Italy), Mauro Barni (University of Siena, Italy)
ClawSentry is an open‑source, framework‑agnostic security supervision gateway designed to protect autonomous large language model (LLM) agents from progressive risks that can arise at four points in the agent control loop: skill admission, invocation‑time intent, execution‑time effect, and post‑action consequence. It introduces a multi‑tier decision engine—deterministic L1, rule‑anchored L2, and read‑only L3—alongside a First‑Use Skill Package Review (FSPR) and an Agent Harness Protocol (AHP) that applies a single policy across multiple agent runtimes without modifying their internals. Evaluation on SkillInject and the SkillsSafety benchmark shows that ClawSentry significantly reduces contextual adversarial skill risk (ASR) while maintaining high task success rates (TSR).
By Kai Wang, Zeming Wei, BiaoJie Zeng, Chang Jin, An Wang, Xiaokun Luan, Zhixiao Lin, Jingjing Qu, Xia Hu, Xingcheng Xu
arXiv:2607. 24893v1 Announce Type: cross Abstract: Multi-agent LLM systems can be attacked by a payload that no single agent ever holds in full: a poisoned tool hides encrypted fragments in its observations, spreads them across several agents, and an external step reassembles and executes them after the run.
By Diego Fernandez Arias, Dev Prashant Mistry, Ren Wang, Yibo Hu
arXiv:2601. 22136v2 Announce Type: replace-cross Abstract: Agent safety benchmarks measure whether a monitor detects harm, not when.
By Gloria Felicia (University of Virginia), Zitha Sasindran (Indian Institute of Science Bangalore), Jinfeng He (Cornell University), Michael Eniolade (University of the Cumberlands), Hemant Kumar (University of Arizona), Milan Hussain Angati (California State University Northridge)
arXiv:2608. 11469v1 Announce Type: cross Abstract: AI agents are rapidly improving in cybersecurity capabilities when the source code is available for analysis, yet much of the software most consequential to cybersecurity, including malware, firmware, and proprietary applications, is available only as binaries.
By Jeremy Spence, Nicholas Assaderaghi, Jinhao Zhu, Nikil Ravi, Raluca Ada Popa, Guannan Wei, Yangruibo Ding, Zhuo Zhang