← Back to all news
arXiv AI By Pengrun Huang, Yiwei Fu, Luoxi Meng, Kamalika Chaudhuri

InferPriv: Evaluating Inferential Privacy Leakage in LLM Assistants

Read the original on arXiv AI →

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.

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 AI.

Related stories

arXiv AI
Aug 19

The Model's Tell: Measuring Context-Leakage Attack Signals with Behavior Gauges

The paper introduces LeakGauge, a method that appends a suffix to a model’s input to gauge the risk of context leakage before decoding. By mapping prefill token probabilities to an attack‑risk score, LeakGauge achieves high AUROC (0.944–0.996) across 11 large language models, including GLM‑5.2 and Kimi‑K3, and remains robust to language changes and different attack styles. The approach also demonstrates sensitivity to internal leakage directions and can be implemented with fewer than 0.5K additional parameters and minimal latency.

By Maosen Zhang, Jianshuo Dong, Boting Lu, Wenyue Li, Xiaoping Zhang, Tianwei Zhang, Jie Zhang, Han Qiu
llmssafety
More like this →
arXiv AI
Sep 25

PrivDrift: Auditing User-Secret Leakage Under Topic Drift in Active LLM Conversations

PrivDrift is a benchmark that tests whether user‑disclosed secrets can still be recovered by large language models after the conversation shifts to unrelated topics. It includes 1,000 controlled multi‑turn dialogues with seeded secrets, topic‑drift turns, and standardized extraction probes. Experiments on three LLMs with extended context windows show that dialogue‑level leakage remains substantial—between 38.7% and 54.6%—and is influenced by model, secret type, and persuasion intensity, while additional topic drift does not reliably reduce leakage.

By Luciano Maldonado
llmsbenchmarkssafety
More like this →