CLIOPATRA: Extracting Private Information from LLM Insights

• URL: http://arxiv.org/abs/2603.09781v1
• Date: Tue, 10 Mar 2026 15:17:14 GMT
• Title: CLIOPATRA: Extracting Private Information from LLM Insights
• Abstract summary: We present CLIOPATRA, the first privacy attack against "privacy-preserving" LLM insight systems.<n>We show that CLIOPATRA can reach close to 100% when Clio is configured with other state-of-the-art models.
• Score: 30.13886480710163
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As AI assistants become widely used, privacy-aware platforms like Anthropic's Clio have been introduced to generate insights from real-world AI use. Clio's privacy protections rely on layering multiple heuristic techniques together, including PII redaction, clustering, filtering, and LLM-based privacy auditing. In this paper, we put these claims to the test by presenting CLIOPATRA, the first privacy attack against "privacy-preserving" LLM insight systems. The attack involves a realistic adversary that carefully designs and inserts malicious chats into the system to break multiple layers of privacy protections and induce the leakage of sensitive information from a target user's chat. We evaluated CLIOPATRA on synthetically generated medical target chats, demonstrating that an adversary who knows only the basic demographics of a target user and a single symptom can successfully extract the user's medical history in 39% of cases by just inspecting Clio's output. Furthermore, CLIOPATRA can reach close to 100% when Clio is configured with other state-of-the-art models and the adversary's knowledge of the target user is increased. We also show that existing ad hoc mitigations, such as LLM-based privacy auditing, are unreliable and fail to detect major leaks. Our findings indicate that even when layered, current heuristic protections are insufficient to adequately protect user data in LLM-based analysis systems.

Related papers

• Steering LLM Viewpoints through Fabricated Evidence Injection [61.22850755490993]
  We introduce a two-phase attack framework that first repackages misleading statements with fabricated rationales, then instruct target LLMs to incorporate these viewpoints when responding to relevant queries.<n>Experiments on BBQ, ToxiGen, and our specialized dataset reveal that commercial LLMs without external safety classifiers remain highly vulnerable.<n>Building on this, we explore multiple defense strategies, among which a tailored safety policy enablesgpt-oss-safeguard to achieve 81% detection rate.
  arXiv  Detail & Related papers  (2026-06-04T14:48:23Z)
• Profiling for Pennies: Unveiling the Privacy Iceberg of LLM Agents [52.02752011119451]
  We investigate privacy perception in the real world through the lens of human awareness.<n>We propose the PrivacyIceberg, which categorizes real-world human privacy risks into three tiers.
  arXiv  Detail & Related papers  (2026-05-07T13:21:44Z)
• When Privacy Meets Recovery: The Overlooked Half of Surrogate-Driven Privacy Preservation for MLLM Editing [61.80513991207956]
  This work focuses on the challenge of how to restore surrogate-driven protected data in diverse MLLM scenarios.<n>We first bridge this research gap by contributing the SPPE (Surrogate Privacy Protected Editable) dataset.<n>We introduce a unified approach that reliably reconstructs private content while preserving the fidelity of MLLM-generated edits.
  arXiv  Detail & Related papers  (2025-12-08T04:59:03Z)
• The Double-edged Sword of LLM-based Data Reconstruction: Understanding and Mitigating Contextual Vulnerability in Word-level Differential Privacy Text Sanitization [53.51921540246166]
  We show that Language Large Models (LLMs) can exploit the contextual vulnerability of DP-sanitized texts.<n>Experiments uncover a double-edged sword effect of LLM reconstructions on privacy and utility.<n>We propose recommendations for using data reconstruction as a post-processing step.
  arXiv  Detail & Related papers  (2025-08-26T12:22:45Z)
• Guarding Your Conversations: Privacy Gatekeepers for Secure Interactions with Cloud-Based AI Models [0.34998703934432673]
  We propose the concept of an "LLM gatekeeper", a lightweight, locally run model that filters out sensitive information from user queries before they are sent to the potentially untrustworthy, though highly capable, cloud-based LLM.<n>Through experiments with human subjects, we demonstrate that this dual-model approach introduces minimal overhead while significantly enhancing user privacy, without compromising the quality of LLM responses.
  arXiv  Detail & Related papers  (2025-08-22T19:49:03Z)
• Malicious LLM-Based Conversational AI Makes Users Reveal Personal Information [9.18715978278858]
  LLM-based Conversational AIs (CAIs) are increasingly used across various domains, but they pose privacy risks.<n>Recent research has demonstrated that LLM-based CAIs could be used for malicious purposes.<n>This study underscores the privacy threats posed by this novel type of malicious LLM-based CAIs.
  arXiv  Detail & Related papers  (2025-06-13T11:19:21Z)
• Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents [33.26308626066122]
  We characterize the notion of contextual privacy for user interactions with Conversational Agents (LCAs)<n>It aims to minimize privacy risks by ensuring that users (sender) disclose only information that is both relevant and necessary for achieving their intended goals.<n>We propose a locally deployable framework that operates between users and LCAs, identifying and reformulating out-of-context information in user prompts.
  arXiv  Detail & Related papers  (2025-02-22T09:05:39Z)
• Evaluating LLM-based Personal Information Extraction and Countermeasures [63.91918057570824]
  Large language model (LLM) based personal information extraction can be benchmarked.<n>LLM can be misused by attackers to accurately extract various personal information from personal profiles.<n> prompt injection can defend against strong LLM-based attacks, reducing the attack to less effective traditional ones.
  arXiv  Detail & Related papers  (2024-08-14T04:49:30Z)
• The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG) [56.67603627046346]
  Retrieval-augmented generation (RAG) is a powerful technique to facilitate language model with proprietary and private data. In this work, we conduct empirical studies with novel attack methods, which demonstrate the vulnerability of RAG systems on leaking the private retrieval database.
  arXiv  Detail & Related papers  (2024-02-23T18:35:15Z)
• Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory [82.7042006247124]
  We show that even the most capable AI models reveal private information in contexts that humans would not, 39% and 57% of the time, respectively. Our work underscores the immediate need to explore novel inference-time privacy-preserving approaches, based on reasoning and theory of mind.
  arXiv  Detail & Related papers  (2023-10-27T04:15:30Z)
• "It's a Fair Game", or Is It? Examining How Users Navigate Disclosure Risks and Benefits When Using LLM-Based Conversational Agents [27.480959048351973]
  The widespread use of Large Language Model (LLM)-based conversational agents (CAs) raises many privacy concerns. We analyzed sensitive disclosures in real-world ChatGPT conversations and conducted semi-structured interviews with 19 LLM-based CA users. We found that users are constantly faced with trade-offs between privacy, utility, and convenience when using LLM-based CAs.
  arXiv  Detail & Related papers  (2023-09-20T21:34:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.