arXiv AI August 19, 2026 By Maosen Zhang, Jianshuo Dong, Boting Lu, Wenyue Li, Xiaoping Zhang, Tianwei Zhang, Jie Zhang, Han Qiu

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

Read the original on arXiv AI →

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.

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.

arXiv Machine Learning

Aug 21

Inadvertent Context Leakage in Language Models

arXiv:2608. 19857v1 Announce Type: new Abstract: For AI agents to be useful beyond simple chat, they must hold sensitive user context such as calendars, credentials, health records, and financial data.

By Jaiden Fairoze, Neal Mangaokar, Kamalika Chaudhuri, Sanjam Garg, Saeed Mahloujifar

llms agents reinforcement-learning safety

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.

llms agents reinforcement-learning safety

arXiv Machine Learning

4d ago

Do LLMs Really Forget? Hidden-State Leakage in Model Unlearning and How to Fix it

arXiv:2609.36612v1 Announce Type: new Abstract: Unlearning in large language models (LLMs) is typically evaluated at the output level, where a model appears to suppress sensitive or undesirable conte...

By Hadi Reisizadeh, Jiajun Ruan, Sijia Liu, Mingyi Hong

llms benchmarks safety

arXiv AI

Aug 5

Your Agentic LLMs Secretly Encode Latent Signals of Indirect Prompt-Injection Exposure

arXiv:2608. 02657v1 Announce Type: cross Abstract: Agentic LLMs are vulnerable to indirect prompt injection (IPI) attacks, e.

By Jianshuo Dong, Yiming Liu, Maosen Zhang, Nan Deng, Xu Peng, Xiaoping Zhang, Tianwei Zhang, Jie Zhang, Han Qiu

llms agents

arXiv AI

Jun 15

From Prompts to Responses: Dual-Sided Data Leakage and Defense in Split Large Language Models

arXiv:2606. 14210v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in privacy-sensitive domains, where users must balance the risk of data exposure through external APIs against the high computational cost of local deployment.

By Zixuan Gu, Xiaojun Ye, Yang Liu

llms fine-tuning benchmarks safety

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

llms benchmarks safety

One email a morning, machine-written

Related stories

Inadvertent Context Leakage in Language Models

Inadvertent Context Leakage in Language Models

Do LLMs Really Forget? Hidden-State Leakage in Model Unlearning and How to Fix it

Your Agentic LLMs Secretly Encode Latent Signals of Indirect Prompt-Injection Exposure

From Prompts to Responses: Dual-Sided Data Leakage and Defense in Split Large Language Models

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