Automated Profile Inference with Language Model Agents

Computer Science > Cryptography and Security [Submitted on 18 May 2025 (v1), last revised 14 Apr 2026 (this version, v2)] Automated Profile Inference with Language Model Agents Yuntao Du, Zitao Li, Bolin Ding, Yaliang Li, Hanshen Xiao, Jingren Zhou, Ninghui Li Impressive progress has been made in automated problem-solving by the collaboration of large language model (LLM) based agents. However, these automated capabilities also open avenues for malicious applications. In this paper, we study a new threat that LLMs pose to online pseudonymity, called automated profile inference, where an adversary can instruct LLMs to automatically collect and extract sensitive personal attributes from publicly available user activities on pseudonymous platforms. We also introduce an automated profiling framework called AutoProfiler to demonstrate and assess the feasibility of such attacks in real-world scenarios. AutoProfiler consists of four specialized LLM agents that work collaboratively to retrieve and process user online activities and generate a profile with extracted personal information. Experimental results on two real-world datasets and one synthetic dataset show that AutoProfiler is highly effective and efficient, and the inferred attributes are both identifiable and sensitive, posing significant privacy risks. We explore mitigation strategies from different perspectives and advocate for increased public awareness of this emerging privacy threat. Comments: Accepted to Findings of the Association for Computational Linguistics (ACL) 2026 Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2505.12402 [cs.CR]   (or arXiv:2505.12402v2 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2505.12402 Focus to learn more Submission history From: Yuntao Du [view email] [v1] Sun, 18 May 2025 13:05:17 UTC (2,618 KB) [v2] Tue, 14 Apr 2026 19:22:31 UTC (2,799 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2025-05 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)