Imagen de Portada

PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Mingxuan, Han, Jiahui, Guo, Dadi, Li, Songze, Wang, Guanchu, Zou, Na, Liu, Dongrui, Hu, Xia
Formato:	Preprint
Publicado:	2026
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

A Trajectory-Based Safety Audit of Clawdbot (OpenClaw)
por: Chen, Tianyu, et al.
Publicado: (2026)

Observable Channels, Not Just Storage: Evaluating Privacy Leakage in LLM Agent Pipelines
por: Huang, Tao, et al.
Publicado: (2026)

BiAxisAudit: A Novel Framework to Evaluate LLM Bias Across Prompt Sensitivity and Response-Layer Divergence
por: Gan, Jialing, et al.
Publicado: (2026)

AudAgent: Automated Auditing of Privacy Policy Compliance in AI Agents
por: Zheng, Ye, et al.
Publicado: (2025)

Privacy-preserving Prompt Personalization in Federated Learning for Multimodal Large Language Models
por: Hou, Sizai, et al.
Publicado: (2025)

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

Demo: TOSense -- What Did You Just Agree to?
por: Chen, Xinzhang, et al.
Publicado: (2025)

CIBER: A Comprehensive Benchmark for Security Evaluation of Code Interpreter Agents
por: Ba, Lei, et al.
Publicado: (2026)

PriRoAgg: Achieving Robust Model Aggregation with Minimum Privacy Leakage for Federated Learning
por: Hou, Sizai, et al.
Publicado: (2024)

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

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

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

NickPay, an Auditable, Privacy-Preserving, Nickname-Based Payment System
por: Quispe, Guillaume, et al.
Publicado: (2025)

SnapAudit: Active Auditing of Differentially Private In-Context Learning via Snapshot-Based Simulation
por: Xia, Yuyang, et al.
Publicado: (2025)

What Makes a Good LLM Agent for Real-world Penetration Testing?
por: Deng, Gelei, et al.
Publicado: (2026)

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

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

Privacy Auditing with Zero (0) Training Run
por: Cebere, Tudor, et al.
Publicado: (2026)

TooBadRL: Trigger Optimization to Boost Effectiveness of Backdoor Attacks on Deep Reinforcement Learning
por: Zhang, Mingxuan, et al.
Publicado: (2025)

What is the Cost of Differential Privacy for Deep Learning-Based Trajectory Generation?
por: Buchholz, Erik, et al.
Publicado: (2025)

Privacy in Theory, Bugs in Practice: Grey-Box Auditing of Differential Privacy Libraries
por: Cebere, Tudor, et al.
Publicado: (2026)

BackdoorIndicator: Leveraging OOD Data for Proactive Backdoor Detection in Federated Learning
por: Li, Songze, et al.
Publicado: (2024)

Arbitrary-Threshold Fully Homomorphic Encryption with Lower Complexity
por: Chang, Yijia, et al.
Publicado: (2025)

Protocol Agent: What If Agents Could Use Cryptography In Everyday Life?
por: De Rossi, Marco
Publicado: (2026)

Enhancing One-run Privacy Auditing with Quantile Regression-Based Membership Inference
por: Liu, Terrance, et al.
Publicado: (2025)

Profiling for Pennies: Unveiling the Privacy Iceberg of LLM Agents
por: Chen, Jiahao, et al.
Publicado: (2026)

Cross-Modal Backdoors in Multimodal Large Language Models
por: Wang, Runhe, et al.
Publicado: (2026)

You Only Anonymize What Is Not Intent-Relevant: Suppressing Non-Intent Privacy Evidence
por: Shen, Weihao, et al.
Publicado: (2026)

Exposing LLM User Privacy via Traffic Fingerprint Analysis: A Study of Privacy Risks in LLM Agent Interactions
por: Zhang, Yixiang, et al.
Publicado: (2025)

"What do you want from theory alone?" Experimenting with Tight Auditing of Differentially Private Synthetic Data Generation
por: Annamalai, Meenatchi Sundaram Muthu Selva, et al.
Publicado: (2024)

Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills
por: Lv, Lijia, et al.
Publicado: (2026)

Holding Secrets Accountable: Auditing Privacy-Preserving Machine Learning
por: Lycklama, Hidde, et al.
Publicado: (2024)

Observational Auditing of Label Privacy
por: Kalemaj, Iden, et al.
Publicado: (2025)

What to Consider When Considering Differential Privacy for Policy
por: Nanayakkara, Priyanka, et al.
Publicado: (2024)

Agent Audit: A Security Analysis System for LLM Agent Applications
por: Zhang, Haiyue, et al.
Publicado: (2026)

CODE: A Contradiction-Based Deliberation Extension Framework for Overthinking Attacks on Retrieval-Augmented Generation
por: Zhang, Xiaolei, et al.
Publicado: (2026)

Audit-or-Cast: Enforcing Honest Elections with Privacy-Preserving Public Verification
por: Rojjha, Aman, et al.
Publicado: (2026)

SilentLedger: Privacy-Preserving Auditing for Blockchains with Complete Non-Interactivity
por: Liu, Zihan, et al.
Publicado: (2025)

VeilAudit: Breaking the Deadlock Between Privacy and Accountability Across Blockchains
por: Qiao, Minhao, et al.
Publicado: (2025)

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI
por: Jin, Heng, et al.
Publicado: (2026)