Cover Image

TraceAegis: Securing LLM-Based Agents via Hierarchical and Behavioral Anomaly Detection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Jiahao, Ruan, Bonan, Yang, Xianglin, Lin, Zhiwei, Liu, Yan, Wang, Yang, Wei, Tao, Liang, Zhenkai
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Heimdallr: Characterizing and Detecting LLM-Induced Security Risks in GitHub CI Workflows
by: Ruan, Bonan, et al.
Published: (2026)

A Large-Scale Evolvable Dataset for Model Context Protocol Ecosystem and Security Analysis
by: Lin, Zhiwei, et al.
Published: (2025)

VulZoo: A Comprehensive Vulnerability Intelligence Dataset
by: Ruan, Bonan, et al.
Published: (2024)

KernJC: Automated Vulnerable Environment Generation for Linux Kernel Vulnerabilities
by: Ruan, Bonan, et al.
Published: (2024)

Propagation-Based Vulnerability Impact Assessment for Software Supply Chains
by: Ruan, Bonan, et al.
Published: (2025)

When MCP Servers Attack: Taxonomy, Feasibility, and Mitigation
by: Zhao, Weibo, et al.
Published: (2025)

Fuzzing the PHP Interpreter via Dataflow Fusion
by: Jiang, Yuancheng, et al.
Published: (2024)

AegisAgent: An Autonomous Defense Agent Against Prompt Injection Attacks in LLM-HARs
by: Wang, Yihan, et al.
Published: (2025)

Aegis: Towards Governance, Integrity, and Security of AI Voice Agents
by: Li, Xiang, et al.
Published: (2026)

Unraveling the Key of Machine Learning-based Android Malware Detection
by: Liu, Jiahao, et al.
Published: (2024)

AegisSat: Securing AI-Enabled SoC FPGA Satellite Platforms
by: Li, Huimin, et al.
Published: (2026)

VULSOLVER: Vulnerability Detection via LLM-Driven Constraint Solving
by: Li, Xiang, et al.
Published: (2025)

TrajAD: Trajectory Anomaly Detection for Trustworthy LLM Agents
by: Liu, Yibing, et al.
Published: (2026)

The Aegis Protocol: A Foundational Security Framework for Autonomous AI Agents
by: Adapala, Sai Teja Reddy, et al.
Published: (2025)

PsyScam: A Benchmark for Psychological Techniques in Real-World Scams
by: Ma, Shang, et al.
Published: (2025)

Detecting and Measuring Security Implications of Entangled Domain Verification in CDN
by: Lin, Ziyu, et al.
Published: (2024)

Research on CNN-BiLSTM Network Traffic Anomaly Detection Model Based on MindSpore
by: Xiang, Qiuyan, et al.
Published: (2025)

Generating API Parameter Security Rules with LLM for API Misuse Detection
by: Liu, Jinghua, et al.
Published: (2024)

AegisMCP: Online Graph Intrusion Detection for Tool-Augmented LLMs on Edge Devices
by: Zhan, Zhonghao, et al.
Published: (2025)

Hierarchical Entropic Diffusion for Ransomware Detection: A Probabilistic Approach to Behavioral Anomaly Isolation
by: Iskorohodov, Vasili, et al.
Published: (2025)

Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections
by: Yang, Xianglin, et al.
Published: (2026)

PentestAgent: Incorporating LLM Agents to Automated Penetration Testing
by: Shen, Xiangmin, et al.
Published: (2024)

Cloud-Edge Collaborative Data Anomaly Detection in Industrial Sensor Networks
by: Yang, Tao, et al.
Published: (2022)

ProvAgent: Threat Detection Based on Identity-Behavior Binding and Multi-Agent Collaborative Attack Investigation
by: Yan, Wenhao, et al.
Published: (2026)

MemoPhishAgent: Memory-Augmented Multi-Modal LLM Agent for Phishing URL Detection
by: Chen, Xuan, et al.
Published: (2026)

A Reinforcement Learning Framework for Robust and Secure LLM Watermarking
by: An, Li, et al.
Published: (2025)

AgentVisor: Defending LLM Agents Against Prompt Injection via Semantic Virtualization
by: Ying, Zonghao, et al.
Published: (2026)

BlockScan: Detecting Anomalies in Blockchain Transactions
by: Yu, Jiahao, et al.
Published: (2024)

SafeHarness: Lifecycle-Integrated Security Architecture for LLM-based Agent Deployment
by: Lin, Xixun, et al.
Published: (2026)

AgentSys: Secure and Dynamic LLM Agents Through Explicit Hierarchical Memory Management
by: Wen, Ruoyao, et al.
Published: (2026)

Trace of the Times: Rootkit Detection through Temporal Anomalies in Kernel Activity
by: Landauer, Max, et al.
Published: (2025)

The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies
by: He, Feng, et al.
Published: (2024)

SINCon: Mitigate LLM-Generated Malicious Message Injection Attack for Rumor Detection
by: Zhang, Mingqing, et al.
Published: (2025)

RulePilot: An LLM-Powered Agent for Security Rule Generation
by: Wang, Hongtai, et al.
Published: (2025)

SoK: Security of Autonomous LLM Agents in Agentic Commerce
by: Mao, Qian'ang, et al.
Published: (2026)

PARIS: A Practical, Adaptive Trace-Fetching and Real-Time Malicious Behavior Detection System
by: Wang, Jian, et al.
Published: (2024)

Multi-Party Private Set Intersection: A Circuit-Based Protocol with Jaccard Similarity for Secure and Efficient Anomaly Detection in Network Traffic
by: Su, Jiuheng, et al.
Published: (2024)

Inverting the Shield: Systematically Generating Safety Tests from Policy Specifications
by: Lu, Xiaoyue, et al.
Published: (2026)

Sentient: Detecting APTs Via Capturing Indirect Dependencies and Behavioral Logic
by: Yan, Wenhao, et al.
Published: (2025)

Trace: Unmasking AI Attack Agents Through Terminal Behavior Fingerprinting
by: Ediga, Murali, et al.
Published: (2026)