The paper introduces the concept of personalized privacy for large language models, allowing user‑specific disclosure preferences to guide information sharing. It presents P3Bench, a benchmark that extends contextual privacy policies with personalized rules, and shows that existing prompt‑based methods often ignore these policies. To improve compliance, the authors propose “Repair”, an inference‑time attention head intervention that aligns model responses with user‑specific privacy rules.
arXiv:2609.35937v1 Announce Type: cross Abstract: While prior work has documented privacy failures in LLM agents, it remains unclear how the presentation of privacy guidance influences their choice o...
arXiv:2608. 09164v1 Announce Type: new Abstract: Aligning large language models (LLMs) with human privacy preferences requires capturing individuals' disclosure boundaries beyond general privacy norms.
arXiv:2606. 09844v1 Announce Type: cross Abstract: Large Language Models (LLMs) alter their privacy behavior based on the perceived identity of their interlocutor.
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.
InferPriv is a new benchmark that evaluates inferential privacy leakage in large language model (LLM) assistants. It measures whether an honest-but-curious recipient can deduce a user’s sensitive attributes from an LLM’s reply during routine tasks, a type of leakage not captured by existing direct‑leakage benchmarks. Testing five frontier models, the study finds that inferential leakage rates (16.2–25.2%) far exceed direct leakage, even when direct leakage is near zero under privacy‑aware prompts.
arXiv:2608.30141v1 Announce Type: cross Abstract: Preference optimization is widely used to align large language models with human preferences, but preference-data composition may also influence priv...
QuasiLeak-Bench is a new benchmark that evaluates large language model (LLM) based privacy detectors on their ability to recover quasi‑evidence groups—sets of weak quasi‑identifiers that jointly reveal private attributes—while respecting sender‑specified disclosure policies. The benchmark uses a reverse‑construction pipeline to generate documents containing verified quasi‑evidence groups and applies automated quality control to produce reliable ground truth at scale. Experiments show that current privacy detectors perform poorly on this task, but a fine‑tuned 4B LLM can outperform the best prompted models, indicating the task is learnable.
arXiv:2610.27213v1 Announce Type: cross Abstract: Personalized large language models (LLMs) increasingly rely on profile-conditioned inference, pairing public requests with rich, user-specific facts....
arXiv:2606. 05004v1 Announce Type: cross Abstract: With the widespread deployment of public large language models (LLMs) such as ChatGPT, protecting user prompt privacy has become an increasingly critical issue.
The paper introduces AIM, a privacy‑aware memory framework that lets multi‑agent, multi‑user large language models manage both private and shared memory. AIM classifies data as private (user‑specific) or public (shared) and enforces index‑level access controls to protect sensitive information while enabling shared knowledge to improve coordination. The authors also present MUMBench, a new dataset for evaluating memory operations in multi‑user settings, and report high accuracy metrics for AIM on this benchmark.
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.
PrivacyFlow introduces a new benchmark, PrivacyBench, and a defense system that separates privacy planning from task execution in autonomous LLM agents. The system traces data provenance, models recipient knowledge, and simulates inference attacks to weigh disclosure risk against task utility, allowing it to minimize or block data sharing. Experiments show that PrivacyFlow reduces privacy failures and increases completed task sequences by 22–55 percentage points, while revealing a tradeoff between privacy, utility, and user autonomy.