Copertina

Ghost Tool Calls: Issue-Time Privacy for Speculative Agent Tools

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Mohammadi, Bardia, Klein, Lars, Arora, Akhil, Bindschaedler, Laurent
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Cryptography and Security Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflows
di: Mohammadi, Bardia, et al.
Pubblicazione: (2026)

Agent Tools Orchestration Leaks More: Dataset, Benchmark, and Mitigation
di: Qiao, Yuxuan, et al.
Pubblicazione: (2025)

IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents
di: An, Hengyu, et al.
Pubblicazione: (2025)

Contextualized Privacy Defense for LLM Agents
di: Wen, Yule, et al.
Pubblicazione: (2026)

NeuroFilter: Privacy Guardrails for Conversational LLM Agents
di: Das, Saswat, et al.
Pubblicazione: (2026)

Beyond Jailbreaking: Auditing Contextual Privacy in LLM Agents
di: Das, Saswat, et al.
Pubblicazione: (2025)

Searching for Privacy Risks in LLM Agents via Simulation
di: Zhang, Yanzhe, et al.
Pubblicazione: (2025)

From Threat to Tool: Leveraging Refusal-Aware Injection Attacks for Safety Alignment
di: Chae, Kyubyung, et al.
Pubblicazione: (2025)

Causality Laundering: Denial-Feedback Leakage in Tool-Calling LLM Agents
di: Chinaei, Mohammad Hossein
Pubblicazione: (2026)

STAC: When Innocent Tools Form Dangerous Chains to Jailbreak LLM Agents
di: Li, Jing-Jing, et al.
Pubblicazione: (2025)

SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer
di: Cheng, Pengzhou, et al.
Pubblicazione: (2024)

Before the Tool Call: Deterministic Pre-Action Authorization for Autonomous AI Agents
di: Uchibeke, Uchi
Pubblicazione: (2026)

MiniScope: A Least Privilege Framework for Authorizing Tool Calling Agents
di: Zhu, Jinhao, et al.
Pubblicazione: (2025)

Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents
di: Ngong, Ivoline, et al.
Pubblicazione: (2025)

The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)
di: Zeng, Shenglai, et al.
Pubblicazione: (2024)

TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories
di: Chen, Yen-Shan, et al.
Pubblicazione: (2026)

Tool Preferences in Agentic LLMs are Unreliable
di: Faghih, Kazem, et al.
Pubblicazione: (2025)

The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration
di: Patil, Vaidehi, et al.
Pubblicazione: (2025)

Improving User Privacy in Personalized Generation: Client-Side Retrieval-Augmented Modification of Server-Side Generated Speculations
di: Salemi, Alireza, et al.
Pubblicazione: (2026)

Privacy-Preserving Retrieval-Augmented Generation with Differential Privacy
di: Koga, Tatsuki, et al.
Pubblicazione: (2024)

ScamAgents: How AI Agents Can Simulate Human-Level Scam Calls
di: Badhe, Sanket
Pubblicazione: (2025)

Beyond Max Tokens: Stealthy Resource Amplification via Tool Calling Chains in LLM Agents
di: Zhou, Kaiyu, et al.
Pubblicazione: (2026)

PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action
di: Shao, Yijia, et al.
Pubblicazione: (2024)

Breaking MCP with Function Hijacking Attacks: Novel Threats for Function Calling and Agentic Models
di: Belkhiter, Yannis, et al.
Pubblicazione: (2026)

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

Do Phone-Use Agents Respect Your Privacy?
di: Tang, Zhengyang, et al.
Pubblicazione: (2026)

Say Something Else: Rethinking Contextual Privacy as Information Sufficiency
di: Xiao, Yunze, et al.
Pubblicazione: (2026)

The Fire Thief Is Also the Keeper: Balancing Usability and Privacy in Prompts
di: Shen, Zhili, et al.
Pubblicazione: (2024)

Security and Privacy Challenges of Large Language Models: A Survey
di: Das, Badhan Chandra, et al.
Pubblicazione: (2024)

How Well Can LLM Agents Simulate End-User Security and Privacy Attitudes and Behaviors?
di: Li, Yuxuan, et al.
Pubblicazione: (2026)

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

Quantifying Association Capabilities of Large Language Models and Its Implications on Privacy Leakage
di: Shao, Hanyin, et al.
Pubblicazione: (2023)

Balancing Innovation and Privacy: Data Security Strategies in Natural Language Processing Applications
di: Liu, Shaobo, et al.
Pubblicazione: (2024)

Shadow in the Cache: Unveiling and Mitigating Privacy Risks of KV-cache in LLM Inference
di: Luo, Zhifan, et al.
Pubblicazione: (2025)

EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage
di: Liao, Zeyi, et al.
Pubblicazione: (2024)

Guarding Your Conversations: Privacy Gatekeepers for Secure Interactions with Cloud-Based AI Models
di: Uzor, GodsGift, et al.
Pubblicazione: (2025)

Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents
di: Li, Xu, et al.
Pubblicazione: (2026)

MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue
di: Wang, Fengxiang, et al.
Pubblicazione: (2024)

Private Memorization Editing: Turning Memorization into a Defense to Strengthen Data Privacy in Large Language Models
di: Ruzzetti, Elena Sofia, et al.
Pubblicazione: (2025)

Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
di: Yang, Wenkai, et al.
Pubblicazione: (2024)