Cover Image

The Dark Side of LLMs: Agent-based Attack Vectors for System-level Compromise

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lupinacci, Matteo, Pironti, Francesco Aurelio, Blefari, Francesco, Romeo, Francesco, Arena, Luigi, Furfaro, Angelo
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ARCeR: an Agentic RAG for the Automated Definition of Cyber Ranges
by: Lupinacci, Matteo, et al.
Published: (2025)

ICSLure: A Very High Interaction Honeynet for PLC-based Industrial Control Systems
by: Pironti, Francesco Aurelio, et al.
Published: (2025)

CyberRAG: An Agentic RAG cyber attack classification and reporting tool
by: Blefari, Francesco, et al.
Published: (2025)

ARPaCCino: An Agentic-RAG for Policy as Code Compliance
by: Romeo, Francesco, et al.
Published: (2025)

MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs
by: Ding, Ruyi, et al.
Published: (2025)

LeakSealer: A Semisupervised Defense for LLMs Against Prompt Injection and Leakage Attacks
by: Panebianco, Francesco, et al.
Published: (2025)

Compromising Embodied Agents with Contextual Backdoor Attacks
by: Liu, Aishan, et al.
Published: (2024)

Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
by: Andriushchenko, Maksym, et al.
Published: (2024)

How stealthy is stealthy? Studying the Efficacy of Black-Box Adversarial Attacks in the Real World
by: Panebianco, Francesco, et al.
Published: (2025)

Breaking Agent Backbones: Evaluating the Security of Backbone LLMs in AI Agents
by: Bazinska, Julia, et al.
Published: (2025)

Attacking Slicing Network via Side-channel Reinforcement Learning Attack
by: Shao, Wei, et al.
Published: (2024)

The Dark Side of Digital Twins: Adversarial Attacks on AI-Driven Water Forecasting
by: Homaei, Mohammadhossein, et al.
Published: (2025)

No More Guessing: a Verifiable Gradient Inversion Attack in Federated Learning
by: Diana, Francesco, et al.
Published: (2026)

Cutting Through Privacy: A Hyperplane-Based Data Reconstruction Attack in Federated Learning
by: Diana, Francesco, et al.
Published: (2025)

The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models
by: Wu, Zihui, et al.
Published: (2024)

CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agent
by: Ning, Liang-bo, et al.
Published: (2025)

Leaky Batteries: A Novel Set of Side-Channel Attacks on Electric Vehicles
by: Marchiori, Francesco, et al.
Published: (2025)

AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration
by: Zhou, Andy, et al.
Published: (2025)

SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems
by: Feng, Yunhao, et al.
Published: (2026)

CoopGuard: Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Round Attacks
by: Li, Siyuan, et al.
Published: (2026)

ToolTweak: An Attack on Tool Selection in LLM-based Agents
by: Sneh, Jonathan, et al.
Published: (2025)

DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent
by: Zhu, Pengyu, et al.
Published: (2025)

Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
by: Zhang, Hanrong, et al.
Published: (2024)

Attribute Inference Attacks for Federated Regression Tasks
by: Diana, Francesco, et al.
Published: (2024)

Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models
by: Braun, Tobias, et al.
Published: (2026)

Enhancing LLM-based Autonomous Driving Agents to Mitigate Perception Attacks
by: Song, Ruoyu, et al.
Published: (2024)

Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-based Decision-Making Systems
by: Jiao, Ruochen, et al.
Published: (2024)

AttackSeqBench: Benchmarking the Capabilities of LLMs for Attack Sequences Understanding
by: Ma, Haokai, et al.
Published: (2025)

Reliable Model Watermarking: Defending Against Theft without Compromising on Evasion
by: Zhu, Hongyu, et al.
Published: (2024)

Vulnerability Disclosure through Adaptive Black-Box Adversarial Attacks on NIDS
by: Ennaji, Sabrine, et al.
Published: (2025)

AdapTools: Adaptive Tool-based Indirect Prompt Injection Attacks on Agentic LLMs
by: Wang, Che, et al.
Published: (2026)

Amplified Vulnerabilities: Structured Jailbreak Attacks on LLM-based Multi-Agent Debate
by: Qi, Senmao, et al.
Published: (2025)

Leveraging Large Language Models for Preliminary Security Risk Analysis: A Mission-Critical Case Study
by: Esposito, Matteo, et al.
Published: (2024)

MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval
by: Srivastava, Saksham Sahai, et al.
Published: (2025)

FlipAttack: Jailbreak LLMs via Flipping
by: Liu, Yue, et al.
Published: (2024)

Behavior-Aware and Generalizable Defense Against Black-Box Adversarial Attacks for ML-Based IDS
by: Ennaji, Sabrine, et al.
Published: (2025)

Security of Internet of Agents: Attacks and Countermeasures
by: Wang, Yuntao, et al.
Published: (2025)

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models
by: Guo, Qiming, et al.
Published: (2025)

SOK: A Taxonomy of Attack Vectors and Defense Strategies for Agentic Supply Chain Runtime
by: Jiang, Xiaochong, et al.
Published: (2026)

LLMs as Hackers: Autonomous Linux Privilege Escalation Attacks
by: Happe, Andreas, et al.
Published: (2023)