Copertina

Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Jiang, Ziyou, Li, Mingyang, Yang, Guowei, Wang, Junjie, Huang, Yuekai, Chang, Zhiyuan, Wang, Qing
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems
di: Chang, Zhiyuan, et al.
Pubblicazione: (2025)

Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning
di: Chang, Zhiyuan, et al.
Pubblicazione: (2026)

Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems
di: Wang, Haowei, et al.
Pubblicazione: (2025)

Fall into a Pit, Gain in a Wit: Cognitive-Guided Harmful Meme Detection via Misjudgment Risk Pattern Retrieval
di: Wang, Wenshuo, et al.
Pubblicazione: (2025)

From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection
di: Wang, Haowei, et al.
Pubblicazione: (2024)

SynAT: Enhancing Security Knowledge Bases via Automatic Synthesizing Attack Tree from Crowd Discussions
di: Jiang, Ziyou, et al.
Pubblicazione: (2026)

Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues
di: Chang, Zhiyuan, et al.
Pubblicazione: (2024)

PatUntrack: Automated Generating Patch Examples for Issue Reports without Tracked Insecure Code
di: Jiang, Ziyou, et al.
Pubblicazione: (2024)

Too Private to Tell: Practical Token Theft Attacks on Apple Intelligence
di: Zhou, Haoling, et al.
Pubblicazione: (2026)

Adversarial Attacks on Reinforcement Learning Agents for Command and Control
di: Dabholkar, Ahaan, et al.
Pubblicazione: (2024)

Making Theft Useless: Adulteration-Based Protection of Proprietary Knowledge Graphs in GraphRAG Systems
di: Wang, Weijie, et al.
Pubblicazione: (2026)

CodePurify: Defend Backdoor Attacks on Neural Code Models via Entropy-based Purification
di: Mu, Fangwen, et al.
Pubblicazione: (2024)

DEFENDCLI: {Command-Line} Driven Attack Provenance Examination
di: Wu, Peilun, et al.
Pubblicazione: (2025)

MalTool: Malicious Tool Attacks on LLM Agents
di: Hu, Yuepeng, et al.
Pubblicazione: (2026)

AdInject: Real-World Black-Box Attacks on Web Agents via Advertising Delivery
di: Wang, Haowei, et al.
Pubblicazione: (2025)

GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning
di: Zhu, Jiani, et al.
Pubblicazione: (2024)

Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in Large Language Models
di: Zheng, Yujia, et al.
Pubblicazione: (2025)

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

Prompt Injection Attack to Tool Selection in LLM Agents
di: Shi, Jiawen, et al.
Pubblicazione: (2025)

From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attacks
di: Zhang, Zhexin, et al.
Pubblicazione: (2024)

Security Attacks on LLM-based Code Completion Tools
di: Cheng, Wen, et al.
Pubblicazione: (2024)

Aggressive Compression Enables LLM Weight Theft
di: Brown, Davis, et al.
Pubblicazione: (2026)

Discovering Command and Control Channels Using Reinforcement Learning
di: Wang, Cheng, et al.
Pubblicazione: (2024)

BM-PAW: A Profitable Mining Attack in the PoW-based Blockchain System
di: Hu, Junjie, et al.
Pubblicazione: (2024)

Fast Energy-Theft Attack on Frequency-Varying Wireless Power without Additional Sensors
di: Wang, Hui, et al.
Pubblicazione: (2025)

Turn Your Face Into An Attack Surface: Screen Attack Using Facial Reflections in Video Conferencing
di: Huang, Yong, et al.
Pubblicazione: (2026)

Learning-based Privacy-Preserving Graph Publishing Against Sensitive Link Inference Attacks
di: Wu, Yucheng, et al.
Pubblicazione: (2025)

QSpy: A Quantum RAT for Circuit Spying and IP Theft
di: Raj, Amal, et al.
Pubblicazione: (2026)

Fingerprint Theft Using Smart Padlocks: Droplock Exploits and Defenses
di: Kerrison, Steve
Pubblicazione: (2024)

AttackLLM: LLM-based Attack Pattern Generation for an Industrial Control System
di: Ahmed, Chuadhry Mujeeb
Pubblicazione: (2025)

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

PenHeal: A Two-Stage LLM Framework for Automated Pentesting and Optimal Remediation
di: Huang, Junjie, et al.
Pubblicazione: (2024)

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

Stealing Maggie's Secrets -- On the Challenges of IP Theft Through FPGA Reverse Engineering
di: Klix, Simon, et al.
Pubblicazione: (2023)

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms
di: He, Sinan, et al.
Pubblicazione: (2025)

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

The Vulnerability of LLM Rankers to Prompt Injection Attacks
di: Yin, Yu, et al.
Pubblicazione: (2026)

Select Me! When You Need a Tool: A Black-box Text Attack on Tool Selection
di: Chen, Liuji, et al.
Pubblicazione: (2025)

VENOMREC: Cross-Modal Interactive Poisoning for Targeted Promotion in Multimodal LLM Recommender Systems
di: Guan, Guowei, et al.
Pubblicazione: (2026)

Evaluating Synthetic Command Attacks on Smart Voice Assistants
di: He, Zhengxian, et al.
Pubblicazione: (2024)