arXiv AI September 12, 2026 By Anna Gazani, Spyridon Kounoupidis, Panagiotis Katsaros, Nikolaos Kekatos, Grigorios Tsoumakas, Georgios Koutidis

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

Read the original on arXiv AI →

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.

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 AI.

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

arXiv AI

4d ago

Trustworthy Agentic AI: A Comprehensive Cybersecurity and Systems Survey on Threat Landscapes, Defense Architectures, and Open Challenges

arXiv:2609.13731v1 Announce Type: new Abstract: The transition from passive foundation models to autonomous, goal-directed agentic AI systems has introduced unprecedented capabilities by coupling rec...

By Seyedakbar Mostafavi

llms agents benchmarks safety

Hugging Face Trending Papers

Jul 22

Defense Against LLM Backdoors using Critical Neuron Isolation Pruning

Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs. Existing defenses generally fall into inference-time detection or training-time mitigation, but face two key limitations.

llms fine-tuning efficiency multimodal benchmarks

arXiv AI

Aug 11

The Anatomy of a Prompt Injection: A Component Model for Structured Analysis

arXiv:2608. 07808v1 Announce Type: cross Abstract: Four years after prompt injection was first identified in 2022, attacks are still predominantly documented as verbatim strings rather than structured exploits, despite advancing agent capabilities and threat actors embedding injections to subvert AI-assisted security analysis.

By Jeremy McHugh

llms rag agents safety

arXiv AI

Jun 9

Automated Framework to Evaluate and Harden LLM System Instructions against Encoding Attacks

arXiv:2604. 01039v2 Announce Type: replace-cross Abstract: System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications.

By Anubhab Sahu, Diptisha Samanta, Reza Soosahabi

llms agents safety

arXiv AI

Jul 23

Defense Against LLM Backdoors using Critical Neuron Isolation Pruning

arXiv:2607. 19894v1 Announce Type: cross Abstract: Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs.

By Yuxi Li, Zhibo Zhang, Kailong Wang, Xingshuo Han, Ling Shi, Haoyu Wang

llms fine-tuning efficiency multimodal benchmarks

One email a morning, machine-written

Related stories

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

Trustworthy Agentic AI: A Comprehensive Cybersecurity and Systems Survey on Threat Landscapes, Defense Architectures, and Open Challenges

Defense Against LLM Backdoors using Critical Neuron Isolation Pruning

The Anatomy of a Prompt Injection: A Component Model for Structured Analysis

Automated Framework to Evaluate and Harden LLM System Instructions against Encoding Attacks

Defense Against LLM Backdoors using Critical Neuron Isolation Pruning