mlsanityData to 14 Oct 2026

IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization

arXiv 2407.02956 ↗First posted 3 Jul 2024cs.CR cs.AI cs.CLcited by 23

Not on the map. Why?

Abstract (arXiv)

In this work, we address the problem of text anonymization where the goal is to prevent adversaries from correctly inferring private attributes of the author, while keeping the text utility, i.e., meaning and semantics. We propose IncogniText, a technique that anonymizes the text to mislead a potential adversary into predicting a wrong private attribute value. Our empirical evaluation shows a reduction of private attribute leakage by more than 90% across 8 different private attributes. Finally, we demonstrate the maturity of IncogniText for real-world applications by distilling its anonymization capability into a set of LoRA parameters associated with an on-device model. Our results show the possibility of reducing privacy leakage by more than half with limited impact on utility.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 14 of its 35 references that are in the map. First posted on arXiv 3 Jul 2024.

Builds on

14 of 35 references.

References · 14

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  3. 2023Qwen Technical Reportcited by 3,344
  4. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,917
  5. 2023Beyond Memorization: Violating Privacy Via Inference with Large Language Modelscited by 175
  6. 2024AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attackscited by 96
  7. 2022The Text Anonymization Benchmark (TAB): A Dedicated Corpus and Evaluation Framework for Text Anonymizationcited by 95
  8. 2023Privacy Issues in Large Language Models: A Surveycited by 60
  9. 2023A Short Survey of Viewing Large Language Models in Legal Aspectcited by 52
  10. 2023Reducing Privacy Risks in Online Self-Disclosures with Language Modelscited by 47
  11. 2023Privacy-Preserving Parameter-Efficient Fine-Tuning for Large Language Model Servicescited by 43
  12. 2023DP-BART for Privatized Text Rewriting under Local Differential Privacycited by 28
2 more
  1. 2024Large Language Models are Advanced Anonymizerscited by 22
  2. 2023Text Sanitization Beyond Specific Domains: Zero-Shot Redaction & Substitution with Large Language Modelscited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 10; 2026: 12.

23 papers.

Sort:

By area:

  1. 2025A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakagecited by 16
  2. 2024Robust Utility-Preserving Text Anonymization Based on Large Language Modelscited by 10
  3. 2025A Survey on Current Trends and Recent Advances in Text Anonymizationcited by 5
  4. 2025How do we measure privacy in text? A survey of text anonymization metricscited by 5
  5. 2025Can Large Language Models Really Recognize Your Name?cited by 4
  6. 2025Self-Refining Language Model Anonymizers via Adversarial Distillationcited by 4
  7. 2026Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMscited by 3
  8. 2025Learning to Erase Private Knowledge from Multi-Documents for Retrieval-Augmented Large Language Modelscited by 2
  9. 2026Private Seeds, Public LLMs: Realistic and Privacy-Preserving Synthetic Data Generationcited by 2
  10. 2025Towards Privacy-Preserving and Personalized Smart Homes via Tailored Small Language Modelscited by 1
  11. 2025A Survey: Towards Privacy and Security in Mobile Large Language Modelscited by 1
  12. 2026Adaptive Text Anonymization: Learning Privacy-Utility Trade-offs via Prompt Optimizationcited by 1
11 more
  1. 2026Subject-level Inference for Realistic Text Anonymization Evaluationcited by 1
  2. 2026GRASP: Reinforcing Language Model Anonymizers with Group Relative Policy Optimizationcited by 1
  3. 2025Retrieval-Confused Generation is a Good Defender for Privacy Violation Attack of Large Language Modelscited by 0
  4. 2025Protecting De-identified Documents from Search-based Linkage Attackscited by 0
  5. 2026From Fragmentation to Integration: Exploring the Design Space of AI Agents for Human-as-the-Unit Privacy Managementcited by 0
  6. 2026Introducing the Privacy-HSD Trade-off: Hate Speech Detection, but not at the Cost of Privacycited by 0
  7. 2026GuardianAgent: Policy-Conditioned Risk-Adaptive Anonymization with Verified Adversarial Escalationcited by 0
  8. 2026PrivBench: A Holistic and Modular Benchmarking Platform for Evaluating Text-to-Text Privatizationcited by 0
  9. 2026GraphProfiler: Source-Linked Sensitive Attribute Inference via Personal Knowledge Graphscited by 0
  10. 2026LLMs as Linguistic Chameleons: Decoupling Semantics and Structure for Privacy-Preserving Communicationcited by 0
  11. 2026AgentDoxx: Agentic Re-identification of Anonymized Text with Web Searchcited by 0