← Back to all news
arXiv AI By Luciano Maldonado

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

Read the original on arXiv AI →

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.

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 4

VoxPrivacy: A Benchmark for Evaluating Interactional Privacy of Speech Language Models

The paper introduces VoxPrivacy, a benchmark for assessing interactional privacy in Speech Language Models (SLMs). It evaluates models on a 32‑hour bilingual dataset across three difficulty tiers, revealing that most open‑source SLMs perform near random on conditional privacy decisions and even strong closed‑source systems struggle with proactive privacy inference. The authors also validate these findings on a real‑speech subset and show that fine‑tuning on a 4,000‑hour training set can improve privacy‑preserving capabilities while maintaining robustness.

By Yuxiang Wang, Hongyu Liu, Dekun Chen, Xueyao Zhang, Zhizheng Wu
llmsfine-tuningbenchmarkssafety
More like this →
Hugging Face Trending Papers
Aug 20

Inadvertent Context Leakage in Language Models

For AI agents to be useful beyond simple chat, they must hold sensitive user context such as calendars, credentials, health records, and financial data. We study whether the mere presence of such secrets in a model's context window introduces hidden correlations into the model's benign outputs, allowing reconstruction even when the model correctly refuses direct extraction.

llmsagentsreinforcement-learningsafety
More like this →