Profiling for Pennies: Unveiling the Privacy Iceberg of LLM Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Jiahao, Zhang, Qi, Lin, Ruixiao, Zhou, Chunyi, Du, Tianyu, Li, Qingming, Zhang, Tong, Li, Junhao, Pu, Yuwen, Ji, Shouling
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918488272011264
author Chen, Jiahao
Zhang, Qi
Lin, Ruixiao
Zhou, Chunyi
Du, Tianyu
Li, Qingming
Zhang, Tong
Li, Junhao
Pu, Yuwen
Ji, Shouling
author_facet Chen, Jiahao
Zhang, Qi
Lin, Ruixiao
Zhou, Chunyi
Du, Tianyu
Li, Qingming
Zhang, Tong
Li, Junhao
Pu, Yuwen
Ji, Shouling
contents Large Language Models (LLMs) have revolutionized how information are collected, aggregated, and reasoned. However, this enables a novel and accessible vector of privacy intrusion: the automated and in-depth personal profiling; this engenders a chilling effect of "peepers everywhere". Existing research primarily unfolds from the training pipeline of LLM, emphasizing the exposure of Personally Identifiable Information (PII) through memorization, while privacy studies from a human-centric perspective remain underexplored. To fill this void, we empirically investigate privacy perception in the real world through the lens of human awareness and the practices of LLM-integrated platforms, revealing a significant dissonance: platforms fail to technically or policy-wise address public privacy concerns. To facilitate a systematic and quantifiable study of privacy risk, we propose the PrivacyIceberg, which categorizes real-world human privacy risks into three tiers: explicitly searched, contextually inferred, and deeply aggregated, based on the sophistication of LLM exploitation. We developed IcebergExplorer to audit privacy exposure, utilizing minimal PII as a search seed to reconstruct high-fidelity profiles, achieving over 90% factual accuracy within 10 minutes at a cost under $3, for real-world scenarios. Additionally, we identify six root causes contributing to such privacy disclosures and propose multi-stakeholder countermeasures for LLM vendors, individuals, and data publishers.
format Preprint
id arxiv_https___arxiv_org_abs_2605_06232
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Profiling for Pennies: Unveiling the Privacy Iceberg of LLM Agents
Chen, Jiahao
Zhang, Qi
Lin, Ruixiao
Zhou, Chunyi
Du, Tianyu
Li, Qingming
Zhang, Tong
Li, Junhao
Pu, Yuwen
Ji, Shouling
Cryptography and Security
Large Language Models (LLMs) have revolutionized how information are collected, aggregated, and reasoned. However, this enables a novel and accessible vector of privacy intrusion: the automated and in-depth personal profiling; this engenders a chilling effect of "peepers everywhere". Existing research primarily unfolds from the training pipeline of LLM, emphasizing the exposure of Personally Identifiable Information (PII) through memorization, while privacy studies from a human-centric perspective remain underexplored. To fill this void, we empirically investigate privacy perception in the real world through the lens of human awareness and the practices of LLM-integrated platforms, revealing a significant dissonance: platforms fail to technically or policy-wise address public privacy concerns. To facilitate a systematic and quantifiable study of privacy risk, we propose the PrivacyIceberg, which categorizes real-world human privacy risks into three tiers: explicitly searched, contextually inferred, and deeply aggregated, based on the sophistication of LLM exploitation. We developed IcebergExplorer to audit privacy exposure, utilizing minimal PII as a search seed to reconstruct high-fidelity profiles, achieving over 90% factual accuracy within 10 minutes at a cost under $3, for real-world scenarios. Additionally, we identify six root causes contributing to such privacy disclosures and propose multi-stakeholder countermeasures for LLM vendors, individuals, and data publishers.
title Profiling for Pennies: Unveiling the Privacy Iceberg of LLM Agents
topic Cryptography and Security
url https://arxiv.org/abs/2605.06232