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
We present nsfaguard, a guardrail framework for securing agentic AI systems against operational threats, such as prompt injection, sensitive information extraction, malicious code requests, dangerous tool misuse, and resource exhaustion. We first introduce the NSFA taxonomy, which organizes 185 risk variants into a CIA-triad-grounded hierarchy and is cross-validated against three well-established OWASP guidelines.
arXiv:2607. 13081v1 Announce Type: cross Abstract: We present nsfaguard, a guardrail framework for securing agentic AI systems against operational threats, such as prompt injection, sensitive information extraction, malicious code requests, dangerous tool misuse, and resource exhaustion.
By SingGuard Team
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)
The paper introduces a black-box framework for evaluating agentic AI systems, focusing on multi-step vulnerabilities that standard single-turn tests miss. It presents a seven-domain taxonomy linking observable behaviors to risk categories, an automated SAGE-RT red-teaming process generating 120 adversarial scenarios per domain, and a human-validated evaluation using LLM judges. Empirical tests on CrewAI and AutoGen agents show significant governance, privacy, and behavior risks, demonstrating the framework’s ability to uncover critical architectural weaknesses without privileged access.
By Divyanshu Kumar, Nitin Aravind Birur, Tanay Baswa, Sahil Agarwal, Prashanth Harshangi
arXiv:2608.00745v2 Announce Type: replace
Abstract: Modern endpoint detection systems face a fundamental tension: signature-based approaches are trivially evaded by polymorphic or adaptive threats, w...
By Zihan Luo
arXiv:2605. 06890v3 Announce Type: replace Abstract: AI agents are promising for high-stakes enterprise workflows, but dependable deployment remains limited because tool-use failures are difficult to diagnose and control.
By Hariom Tatsat, Ariye Shater
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:2606. 01494v1 Announce Type: cross Abstract: Agent skills extend AI agents with reusable instructions, tools, scripts, references, and workflows, establishing a security boundary distinct from both model safety and traditional package-malware detection.
By Vincent Koc, Patrick Erichsen, Jacob Tomlinson, Agustin Rivera, Michael Appel, Nir Paz
arXiv:2607. 28460v1 Announce Type: new Abstract: A major issue in Security Operations Centers (SOCs) is alert fatigue, as the number of detections reported is more than staff can triage in a given day.
By Amol Khanna, Manu Nandan, Cristian Viorel Popa, Joan Pujol-Roig, Diana Bolocan, Laura Vasilie, Alexandru Apostu, Chase Helwig, Mihaela Gaman, Michael Brautbar, Edward Raff, Chase Midler, Sven Krasser
arXiv:2604.01151v3 Announce Type: replace
Abstract: As LLM agents are increasingly deployed in multi-agent systems, they introduce risks of covert coordination that may evade standard forms of human...
By Aaron Rose, Carissa Cullen, Sahar Abdelnabi, Philip Torr, Brandon Gary Kaplowitz, Christian Schroeder de Witt
arXiv:2606. 18356v1 Announce Type: cross Abstract: Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent memory, send messages, modify databases, or trigger harmful code and tool effects.
By Yuchuan Tian, Mengyu Zheng, Haocheng Mei, Ye Yuan, Chao Xu, Xinghao Chen, Hanting Chen, Yu Wang