Monitoring & Detection
7 resourcesDefenses & Mitigations
Anomaly detection, behavioral analysis, and drift monitoring
IoT-Aided Self-Adaptive Routing for Flying Ad Hoc Network Using Gauss-Markov Mobility Model
Oroos Arshi, Tarandeep Kaur Bhatia, Inam Ullah Khan + 2 more
Introduction: Unmanned aerial vehicles (UAVs) are low-cost, easy to deploy, and can be integrated with IoT to solve human-related problems. They have applications in military and civil sectors, such as forest fire detection, sports monitoring, agriculture, and border surveillance. UAV-based applications can be signal or multi-system.
MCPShield: Content-Aware Attack Detection for LLM Agent Tool-Call Traffic
Sultan Zavrak
The Model Context Protocol (MCP) has become a widely adopted interface for LLM agents to invoke external tools, yet learned monitoring of MCP tool-call traffic remains underexplored. In this article, MCPShield is presented as an attack detection framework for MCP tool-call traffic that encodes each agent session as a graph (tool calls as nodes, sequential and data-flow links as edges), enriches nodes with sentence-embedding features over arguments and responses, and classifies sessions as benign
MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning
Yizhe Zeng, Wei Zhang, Yunpeng Li + 3 more
While Chain-of-Thought (CoT) prompting has become a standard paradigm for eliciting complex reasoning capabilities in Large Language Models, it inadvertently exposes a new attack surface for backdoor attacks. Existing CoT backdoor attacks typically manipulate the intermediate reasoning steps to steer the model toward incorrect answers. However, these corrupted reasoning traces are readily detected by prevalent process-monitoring defenses. To address this limitation, we introduce MirageBackdoor(M
Modeling Implicit Conflict Monitoring Mechanisms against Stereotypes in LLMs
Jingshen Zhang, Bo Wang, Yanlin Fu + 4 more
In this paper, we study an emergent self-debiasing mechanisms against stereotypical content in Large Language Models (LLMs). Unlike traditional safety mechanisms that are primarily triggered by explicit input-level stimuli, self-debiasing mechanisms can involve generation-time intrinsic correction that are not directly reducible to surface-level prompt. Motivated by conflict-monitoring and response-inhibition accounts in cognitive neuroscience, we propose COCO, a contrastive causal method design
Hybrid ML-LLM Pipeline for Non-Governance IT Audits
Kaung Myat Naing, Talha Ali, Mohammed Ouannass
Organizations outside formal governance frameworks often lack cybersecurity audit tools, making anomaly detection and risk evaluation difficult. This paper presents an AI-enhanced auditing framework for non-governance IT environments. Using the UNSW-NB15 dataset, we evaluate four machine-learning models: Isolation Forest, Logistic Regression, Gradient Boosting, and XGBoost, identifying complementary strengths that motivate a two-stage filter for suspicious network flows. Flagged flows ar
HSAE: A Hybrid Unsupervised Autoencoder for Zero-Day Attack Detection in Realistic Environments
Fabiano C. da Silva, Franklin A. M. Venceslau, Rafael R. de Souza + 1 more
Research Context: Anomaly detection in computer networks is essential for cybersecurity, especially in complex environments like corporate and IoT networks that face emerging threats. Scientific and/or Practical Problem: Traditional Intrusion Detection Systems (IDS) struggle to identify zero-day attacks, creating significant security gaps. Signature-based approaches fail against unknown threats, while supervised models require large volumes of labeled data rarely available in practice. U
Vigil: LLM Prompt Injection Detection and Defense Toolkit
DeadBits — GitHub
Open-source scanner for detecting prompt injections using vector similarity, YARA rules, text classifiers, and canary tokens.