Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sun, Guoheng, Wang, Ziyao, Zhao, Xuandong, Tian, Bowei, Shen, Zheyu, He, Yexiao, Xing, Jinming, Li, Ang
Format:	Preprint
Publié:	2025
Sujets:	Cryptography and Security Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Predictive Auditing of Hidden Tokens in LLM APIs via Reasoning Length Estimation
par: Wang, Ziyao, et autres
Publié: (2025)

Prada: Black-Box LLM Adaptation with Private Data on Resource-Constrained Devices
par: Wang, Ziyao, et autres
Publié: (2025)

CoIn: Counting the Invisible Reasoning Tokens in Commercial Opaque LLM APIs
par: Sun, Guoheng, et autres
Publié: (2025)

Towards Building Non-Fine-Tunable Foundation Models
par: Wang, Ziyao, et autres
Publié: (2026)

Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs
par: Cai, Will, et autres
Publié: (2025)

Sealing the Audit-Runtime Gap for LLM Skills
par: Shen, Tingda, et autres
Publié: (2026)

Hunting the Ghost: Towards Automatic Mining of IoT Hidden Services
par: Dong, Shuaike, et autres
Publié: (2025)

DiffAudit: Auditing Privacy Practices of Online Services for Children and Adolescents
par: Figueira, Olivia, et autres
Publié: (2024)

Curator Attack: When Blackbox Differential Privacy Auditing Loses Its Power
par: Wang, Shiming, et autres
Publié: (2024)

Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy
par: Ren, Jie, et autres
Publié: (2025)

MALF: A Multi-Agent LLM Framework for Intelligent Fuzzing of Industrial Control Protocols
par: Ning, Bowei, et autres
Publié: (2025)

Moderator: Moderating Text-to-Image Diffusion Models through Fine-grained Context-based Policies
par: Wang, Peiran, et autres
Publié: (2024)

GoAT-X: A Graph of Auditing Thoughts for Securing Token Transactions in Cross-Chain Contracts
par: Feng, Zijun, et autres
Publié: (2026)

Tight Privacy Audit in One Run
par: Xiang, Zihang, et autres
Publié: (2025)

LLM-SmartAudit: Advanced Smart Contract Vulnerability Detection
par: Wei, Zhiyuan, et autres
Publié: (2024)

Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model
par: Cebere, Tudor, et autres
Publié: (2024)

Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Models
par: Xiong, Junjie, et autres
Publié: (2025)

When Skills Lie: Hidden-Comment Injection in LLM Agents
par: Wang, Qianli, et autres
Publié: (2026)

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation
par: Zhu, Wentian, et autres
Publié: (2025)

Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption
par: Liu, Yepeng, et autres
Publié: (2025)

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

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

InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks
par: Zheng, Xinyao, et autres
Publié: (2024)

SA2FE: A Secure, Anonymous, Auditable, and Fair Edge Computing Service Offloading Framework
par: Wang, Xiaojian, et autres
Publié: (2025)

Cross-Service Token: Finding Attacks in 5G Core Networks
par: Chen, Anqi, et autres
Publié: (2025)

Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM Watermarking
par: Gu, Tianle, et autres
Publié: (2025)

Securing LLM Agents Need Intent-to-Execution Integrity
par: Qu, Wenjie, et autres
Publié: (2026)

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

Privacy Audit as Bits Transmission: (Im)possibilities for Audit by One Run
par: Xiang, Zihang, et autres
Publié: (2025)

Privacy-Preserving Billing for Local Energy Markets
par: Alqahtani, Eman, et autres
Publié: (2024)

Everyone Needs AIR: An Agnostic Incident Reporting Framework for Cybersecurity in Operational Technology
par: Vidal, Nubio, et autres
Publié: (2025)

Auditing Private Prediction
par: Chadha, Karan, et autres
Publié: (2024)

Invisible Watermarks, Visible Gains: Steering Machine Unlearning with Bi-Level Watermarking Design
par: Sun, Yuhao, et autres
Publié: (2025)

Snorkeling in dark waters: A longitudinal surface exploration of unique Tor Hidden Services (Extended Version)
par: Barredo-Valenzuela, Alfonso Rodriguez, et autres
Publié: (2025)

A Managed Tokens Service for Securely Keeping and Distributing Grid Tokens
par: Bhat, Shreyas, et autres
Publié: (2025)

Invisible Image Watermarks Are Provably Removable Using Generative AI
par: Zhao, Xuandong, et autres
Publié: (2023)

Auditing Pay-Per-Token in Large Language Models
par: Velasco, Ander Artola, et autres
Publié: (2025)

Blockchain-Anchored Audit Trail Model for Transparent Inter-Operator Settlement
par: Kunthu, Balakumar Ravindranath, et autres
Publié: (2025)

Invisible Trails? An Identity Alignment Scheme based on Online Tracking
par: Shi, Ruisheng, et autres
Publié: (2026)

ISSF: The Intelligent Security Service Framework for Cloud-Native Operation
par: Yan, Yikuan, et autres
Publié: (2024)