arXiv Machine Learning June 9, 2026 By Bilal Hussain, Muhammad Bilal, Tan Li, Haris Pervaiz, Xiao Tang, Qinghe Du, Fawad Ahmad, Muhammad Azhar, Jun Zhang

AI-Native Closed-Loop Security for 6G-Enabled Cyber-Physical Systems: From Edge Detection to Network-Wide Mitigation

Read the original on arXiv Machine Learning →

arXiv:2606. 08173v1 Announce Type: cross Abstract: In sixth-generation (6G) networks, billions of cyber-physical systems (CPSs) - autonomous vehicles, smart grids, industrial robots, and remote-surgical equipment - will run over ultra-reliable low-latency slices, collapsing the gap between a remote breach and physical harm to milliseconds, a budget perimeter firewalls and centralised security operations centres cannot meet.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 16

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge

arXiv:2607. 13088v1 Announce Type: cross Abstract: Large Language Models (LLMs) are rapidly moving from research settings into the wild, deployed on enterprise infrastructure, personal devices, and edge platforms.

By Ren-Yi Huang, Mingchen Li, Dumindu Samaraweera, Morris Chang

llms efficiency safety

arXiv Machine Learning

Aug 10

Dual-Node NVIDIA DGX Spark over Tailscale: A Remote-Access Testbed for Distributed LLM Training and Cyber-Threat-Intelligence Fine-Tuning

arXiv:2608. 07226v1 Announce Type: cross Abstract: Compact AI systems make local language-model experimentation increasingly accessible, yet practical evidence for multi-node training on desktop-class accelerators remains limited.

By Vasanth Iyer

llms fine-tuning efficiency data-engineering

arXiv AI

Sep 12

Architecting the Secure AI-SOC: A Neurosymbolic Framework for Pipeline Integrity and Threat Mitigation

The paper proposes a neurosymbolic defense architecture for AI-enhanced Security Operations Centers (AI‑SOCs) that protects against indirect prompt injection via log poisoning. It combines deterministic SIEM decoders as a pre‑filter with NeMo Guardrails for semantic validation, and adds a closed‑loop telemetry system for Human‑in‑the‑Loop visibility. Experimental results mapped to the MITRE ATLAS taxonomy show the approach effectively dismantles promptware kill chains and delivers a resilient, observable defense for next‑generation AI‑SOCs.

By Anna Gazani, Spyridon Kounoupidis, Panagiotis Katsaros, Nikolaos Kekatos, Grigorios Tsoumakas, Georgios Koutidis

llms rag safety

arXiv Machine Learning

2d ago

Cybersecurity in Edge Computing: A Trust-Aware Federated Hybrid Intrusion Detection Framework

arXiv:2609.39584v1 Announce Type: cross Abstract: Edge computing has emerged as a critical computing paradigm in modern distributed systems by migrating data processing closer to end users and Intern...

By Zawad Yalmie Sazid, Robert Abbas

agents benchmarks safety

arXiv AI

Jul 3

Less Data, More Security: Advancing Cybersecurity LLMs Specialization via Resource-Efficient Domain-Adaptive Continuous Pre-training with Minimal Tokens

arXiv:2507. 02964v2 Announce Type: replace-cross Abstract: The increasing scale of AI workloads demands High-Performance Computing (HPC) infrastructure and training methodologies that are both scalable and sustainable.

By Salahuddin Salahuddin, Ahmed Hussain, Jussi L\"opp\"onen, Toni Jutila

llms fine-tuning benchmarks

arXiv AI

Jun 30

RIPA: Sensory-Vector Prompt Injection Attacks on LLM-Controlled ROS 2 Robots

arXiv:2606. 28649v1 Announce Type: cross Abstract: We present RIPA, the first systematic multi-channel empirical study of prompt injection attacks delivered through the sensory pipeline of a ROS 2-based LLM-controlled robotic system.

By Nima Dorzhiev

llms computer-vision robotics multimodal

One email a morning, machine-written

Related stories

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge

Dual-Node NVIDIA DGX Spark over Tailscale: A Remote-Access Testbed for Distributed LLM Training and Cyber-Threat-Intelligence Fine-Tuning

Architecting the Secure AI-SOC: A Neurosymbolic Framework for Pipeline Integrity and Threat Mitigation

Cybersecurity in Edge Computing: A Trust-Aware Federated Hybrid Intrusion Detection Framework

Less Data, More Security: Advancing Cybersecurity LLMs Specialization via Resource-Efficient Domain-Adaptive Continuous Pre-training with Minimal Tokens

RIPA: Sensory-Vector Prompt Injection Attacks on LLM-Controlled ROS 2 Robots