Imagen de Portada

Invisible Tokens, Visible Bills: The Urgent Need to Audit Hidden Operations in Opaque LLM Services

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Sun, Guoheng, Wang, Ziyao, Zhao, Xuandong, Tian, Bowei, Shen, Zheyu, He, Yexiao, Xing, Jinming, Li, Ang
Formato:	Preprint
Publicado:	2025
Materias:	Cryptography and Security Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Predictive Auditing of Hidden Tokens in LLM APIs via Reasoning Length Estimation
por: Wang, Ziyao, et al.
Publicado: (2025)

Prada: Black-Box LLM Adaptation with Private Data on Resource-Constrained Devices
por: Wang, Ziyao, et al.
Publicado: (2025)

CoIn: Counting the Invisible Reasoning Tokens in Commercial Opaque LLM APIs
por: Sun, Guoheng, et al.
Publicado: (2025)

Towards Building Non-Fine-Tunable Foundation Models
por: Wang, Ziyao, et al.
Publicado: (2026)

Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs
por: Cai, Will, et al.
Publicado: (2025)

Sealing the Audit-Runtime Gap for LLM Skills
por: Shen, Tingda, et al.
Publicado: (2026)

Hunting the Ghost: Towards Automatic Mining of IoT Hidden Services
por: Dong, Shuaike, et al.
Publicado: (2025)

DiffAudit: Auditing Privacy Practices of Online Services for Children and Adolescents
por: Figueira, Olivia, et al.
Publicado: (2024)

Curator Attack: When Blackbox Differential Privacy Auditing Loses Its Power
por: Wang, Shiming, et al.
Publicado: (2024)

Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy
por: Ren, Jie, et al.
Publicado: (2025)

MALF: A Multi-Agent LLM Framework for Intelligent Fuzzing of Industrial Control Protocols
por: Ning, Bowei, et al.
Publicado: (2025)

Moderator: Moderating Text-to-Image Diffusion Models through Fine-grained Context-based Policies
por: Wang, Peiran, et al.
Publicado: (2024)

GoAT-X: A Graph of Auditing Thoughts for Securing Token Transactions in Cross-Chain Contracts
por: Feng, Zijun, et al.
Publicado: (2026)

Tight Privacy Audit in One Run
por: Xiang, Zihang, et al.
Publicado: (2025)

LLM-SmartAudit: Advanced Smart Contract Vulnerability Detection
por: Wei, Zhiyuan, et al.
Publicado: (2024)

Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model
por: Cebere, Tudor, et al.
Publicado: (2024)

Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Models
por: Xiong, Junjie, et al.
Publicado: (2025)

When Skills Lie: Hidden-Comment Injection in LLM Agents
por: Wang, Qianli, et al.
Publicado: (2026)

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation
por: Zhu, Wentian, et al.
Publicado: (2025)

Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption
por: Liu, Yepeng, et al.
Publicado: (2025)

Reinforcement Learning-Based Approaches for Enhancing Security and Resilience in Smart Control: A Survey on Attack and Defense Methods
por: Zhang, Zheyu
Publicado: (2024)

PhantomLint: Principled Detection of Hidden LLM Prompts in Structured Documents
por: Murray, Toby
Publicado: (2025)

InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks
por: Zheng, Xinyao, et al.
Publicado: (2024)

SA2FE: A Secure, Anonymous, Auditable, and Fair Edge Computing Service Offloading Framework
por: Wang, Xiaojian, et al.
Publicado: (2025)

Cross-Service Token: Finding Attacks in 5G Core Networks
por: Chen, Anqi, et al.
Publicado: (2025)

Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM Watermarking
por: Gu, Tianle, et al.
Publicado: (2025)

Securing LLM Agents Need Intent-to-Execution Integrity
por: Qu, Wenjie, et al.
Publicado: (2026)

LLM-CEG: Extending the Classification Error Gauge Framework for Privacy Auditing of Large Language Models
por: Mivule, Kato
Publicado: (2026)

Privacy Audit as Bits Transmission: (Im)possibilities for Audit by One Run
por: Xiang, Zihang, et al.
Publicado: (2025)

Privacy-Preserving Billing for Local Energy Markets
por: Alqahtani, Eman, et al.
Publicado: (2024)

Everyone Needs AIR: An Agnostic Incident Reporting Framework for Cybersecurity in Operational Technology
por: Vidal, Nubio, et al.
Publicado: (2025)

Auditing Private Prediction
por: Chadha, Karan, et al.
Publicado: (2024)

Invisible Watermarks, Visible Gains: Steering Machine Unlearning with Bi-Level Watermarking Design
por: Sun, Yuhao, et al.
Publicado: (2025)

Snorkeling in dark waters: A longitudinal surface exploration of unique Tor Hidden Services (Extended Version)
por: Barredo-Valenzuela, Alfonso Rodriguez, et al.
Publicado: (2025)

A Managed Tokens Service for Securely Keeping and Distributing Grid Tokens
por: Bhat, Shreyas, et al.
Publicado: (2025)

Invisible Image Watermarks Are Provably Removable Using Generative AI
por: Zhao, Xuandong, et al.
Publicado: (2023)

Auditing Pay-Per-Token in Large Language Models
por: Velasco, Ander Artola, et al.
Publicado: (2025)

Blockchain-Anchored Audit Trail Model for Transparent Inter-Operator Settlement
por: Kunthu, Balakumar Ravindranath, et al.
Publicado: (2025)

Invisible Trails? An Identity Alignment Scheme based on Online Tracking
por: Shi, Ruisheng, et al.
Publicado: (2026)

ISSF: The Intelligent Security Service Framework for Cloud-Native Operation
por: Yan, Yikuan, et al.
Publicado: (2024)