arXiv AI
Jun 18
RedactionBench
arXiv:2606. 18782v1 Announce Type: cross Abstract: Large Language Models are increasingly applied to sensitive domains that require redaction of personally identifiable information (PII).
ASIRF: An Agentic Framework for Context-Dependent Sensitive Information Redaction
ASIRF (Agentic Sensitive Information Redaction Framework) is a system that retrieves domain‑specific definitions of sensitive information from a flexible knowledge base at inference time, eliminating the need for retraining when adapting to new domains. It offers two architectures—a three‑call multi‑agent pipeline and a single‑agent variant—and has been evaluated on ten small open‑weight models across eight datasets, including out‑of‑distribution fictional domains. In 68 of 80 model‑domain combinations (85 %), ASIRF’s recall surpasses that of the OpenAI Privacy Filter, with most shortfalls limited to the filter’s training‑distribution domains.
Related stories
arXiv AI
Jun 24
Privacy-Preserving RAG via Multi-Agent Semantic Rewriting: Achieving Confidentiality Without Compromising Contextual Fidelity
arXiv:2606. 24623v1 Announce Type: cross Abstract: Retrieval-Augmented Generation enhances large language models by incorporating external knowledge, but deploying it in sensitive scenarios risks privacy leakage via malicious prompts.
arXiv AI
Jul 2
NeuroFilter: Activation-Based Guardrails for Privacy-Conscious LLM Agents
arXiv:2601. 14660v2 Announce Type: replace-cross Abstract: Agentic Large Language Models (LLMs) are models able to reason, plan, and execute tools over unstructured data.
arXiv AI
Aug 18
AWED-PIPER: Agents, Web Applications & Expert Detectors for Personally Identifiable Information Protection & Fine-grained Named Entity Recognition across 36 languages for 6.6 Billion Speakers
arXiv:2601. 10161v3 Announce Type: replace-cross Abstract: Named Entity Recognition (NER) and Personally Identifiable Information (PII) anonymization are critical tasks in Natural Language Processing (NLP) for information extraction and privacy preservation.
arXiv Computation and Language
Sep 11
On the Impact of Anonymization on the Performance of Large Language Models
The paper systematically studies how anonymizing input data affects large language models (LLMs). Five prominent LLMs were evaluated on eleven benchmarks, comparing performance on original versus pseudonymized inputs. Results show that anonymization generally degrades performance, with larger drops for more capable models and task-dependent effects; reversible anonymization preserves entity uniqueness better than irreversible redaction, and prompting about anonymization offers no benefit.
arXiv AI
Jun 18
Redact or Keep? A Fully Local AI Cascade for Educational Dialogue De-Identification
arXiv:2606. 18372v1 Announce Type: cross Abstract: Educational dialogue is a valuable but sensitive resource for research: the same transcripts that capture authentic learning often capture personally identifiable information (PII) entangled with curricular content, where "Riemann" may refer to a real student or to a mathematical concept.
arXiv Computation and Language
Sep 1
CARE: Privacy-Compliant Agentic Reasoning with Evidence Discordance
The paper introduces MIMIC-DOS, a dataset derived from MIMIC-IV that focuses on ICU cases where patient symptoms and medical signs are discordant. It presents CARE, a privacy‑compliant multi‑stage agentic reasoning framework that uses a proprietary LLM to generate structured categories and transitions, while a local LLM performs evidence acquisition and decision‑making. In retrospective evaluations on MIMIC‑DOS, CARE outperforms other LLMs and agentic workflows, demonstrating stronger handling of conflicting clinical evidence while preserving patient privacy.
arXiv AI
Aug 20
Redakto - The Incognito Tab for LLMs
Redakto is a new tool designed to anonymize text before it is processed by large language models (LLMs). It offers state‑of‑the‑art redaction of personally identifiable information (PII) and pseudonymization, accessible via a web interface, REST APIs, and model context protocol hooks. The authors evaluate its performance on legal and medical datasets, showing that anonymized texts retain utility comparable to the originals, enabling LLM tasks without significant loss of effectiveness.
arXiv Machine Learning
Aug 20
Model Card for OpenAI Privacy Filter
The OpenAI Privacy Filter is a 1.5‑billion‑parameter, bidirectional token‑classification model that detects and redacts personally identifiable information and secrets in unstructured text. It is built from an autoregressive checkpoint, converted into a banded‑attention classifier, and uses a constrained Viterbi decoder to produce coherent spans across eight privacy categories in a single forward pass. The model supports configurable precision‑recall tradeoffs, a 128,000‑token context window, and is designed for efficient local deployment and domain‑specific fine‑tuning as a data‑minimization component within layered privacy workflows.
arXiv AI
Jun 29
Agentic AI-Powered Re-Identification: An Emerging, Scalable Threat to Mobility Microdata Privacy
arXiv:2606. 27936v1 Announce Type: cross Abstract: The widespread collection of fine-grained location data by commercial data brokers creates a re-identification risk that is not widely recognised by the public.
Hugging Face Trending Papers
Aug 3
MNC: Scope-Bound Semantic Declassification for Private LLM-Agent Communication
Multi-agent large language model (LLM) systems can expose protected state through internal messages, tool arguments, logs, and persistent memory even when their public outputs appear innocuous. Existing privacy prompts, redaction methods, and source-level access controls restrict surface content or data access, but do not specify what a legitimately informed agent should disclose or how that disclosure may be reused downstream.
Hugging Face Trending Papers
Jun 22
Have You Ever Seen Them? Entity-level Membership Inference through Interrogating Large Language Models
Large Language Models (LLMs) raise growing concerns about privacy leakage and copyright compliance. Membership inference is a key tool for assessing such risks, but existing studies mainly focus on whether specific samples or sample-based data units are used for training.