← Back to all news
arXiv Computation and Language By Ziwen Li, Jianing Wen, Tianshi Li

LLM Anonymization Against Agentic Re-Identification

Read the original on arXiv Computation and Language →

The paper introduces AURA, an LLM-powered mask‑reconstruct framework for anonymizing text while preserving utility. It decouples privacy localization from utility‑preserving reconstruction and uses adversarial checks to select candidates. Experiments on real‑user interview transcripts show that AURA achieves the lowest agentic re‑identification rates among non‑DP methods and retains more contextual utility than prior LLM anonymizers.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv AI
Sep 12

Demystifying the Privacy-Utility Trade-off in LLM Interactions

The paper investigates how privacy-preserving sanitization of user context in large language model (LLM) interactions affects downstream performance. It identifies three mechanisms—Context‑Dependent Utility, Strategic Adaptation, and Combinatorial Interplay—that explain when and how to sanitize data. Based on these insights, the authors propose an intent‑driven local protection framework using a lightweight model (Veilmind‑4B) to dynamically extract, sanitize, and restore context, achieving lower privacy leakage while maintaining higher utility than existing baselines.

By Zhenhua Liu, Zhanxu Xie, Junjie Yu, Tong Zhu, Lijun Li, Wenliang Chen
llmssafety
More like this →
arXiv Machine Learning
Aug 5

DP-MemView: A Memory Interface for Attribute-Level Transcript Privacy in Long-Term LLM Agents

arXiv:2608. 03130v1 Announce Type: cross Abstract: Long-term memory enables persistent personalization in LLM agents, but repeated memory-conditioned responses can cumulatively reveal protected attributes even when they are never stated explicitly.

By Jong Wook Kim, Byoungjae Min, Kennedy Edemacu, Yoonhyuk Choi, Sae-Hong Cho, Beakcheol Jang
llmsagentsbenchmarkssafety
More like this →
arXiv Machine Learning
Sep 3

Context Inference Attacks Without Jailbreaks

The paper investigates privacy risks in agentic AI systems that assemble sensitive data into a hidden context before responding. It introduces context‑inference attacks, a security game that evaluates how well attackers can recover this hidden context under varying levels of knowledge and indirect delivery. Experiments show that even with controls such as instructions not to disclose, logit suppression, and context dilution, agents can leak significant contextual information, achieving high success rates across multiple attack settings.

By Prince Jha, Samuele Poppi, Nils Lukas
agentsmultimodalsafety
More like this →