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
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
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
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.
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.
By Saswat Das, Ferdinando Fioretto
arXiv:2602. 01146v2 Announce Type: replace Abstract: Conversational assistants are increasingly integrating long-term memory with large language models (LLMs).
By Sidharth Pulipaka, Oliver Chen, Manas Sharma, Taaha S Bajwa, Vyas Raina, Ivaxi Sheth
arXiv:2608. 08300v1 Announce Type: new Abstract: Conversational assistants increasingly rely on persistent long-term memory to personalize responses across sessions.
By Hakeem Hannoon, Andrew Zhao, Mihir Narayan, Sharvin Goyal, Ivaxi Sheth
The paper argues that large language models (LLMs) lack a private working memory, which is essential for tasks that require hidden state, such as interactive games. It introduces Private State Interactive Tasks (PSITs) and proves that chat-based LLMs cannot maintain a secret state while producing consistent public responses. Empirical tests confirm that standard LLMs and retrieval-based baselines fail, while a new architecture with explicit private memory succeeds.
By Davide Baldelli, Ali Parviz, Amal Zouaq, Sarath Chandar
arXiv:2609.14003v1 Announce Type: cross
Abstract: Personal AI agents built on large language models (LLMs) are increasingly given access to a user's private data and communications in order to provid...
By Minsun Shim, Ramisha Raida Karim, Ruthwik Jakkula, Kaiwen Zhou, Xin Liu, Xin Eric Wang, Zhou Li
arXiv:2606. 09844v1 Announce Type: cross Abstract: Large Language Models (LLMs) alter their privacy behavior based on the perceived identity of their interlocutor.
By Faouzi El Yagoubi, Godwin Badu-Marfo, Ranwa Al Mallah
SpeechLLMs used in professional settings often undergo domain customisation through prompts or fine‑tuning, which can inadvertently cause the model to transcribe phonetically similar words from its context or training data, leaking private information. The authors systematically investigate this overlooked privacy risk, creating benchmarks to measure leakage rates for both prompting and fine‑tuning, and find that both mechanisms cause measurable leakage that compounds when combined. They evaluate a prompt‑level mitigation strategy and analyse the accuracy‑leakage trade‑off, concluding that fine‑tuning without context prompts offers the best balance between performance and privacy.
By Maike Z\"ufle, Jan Niehues
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.
By Jong Wook Kim, Byoungjae Min, Kennedy Edemacu, Yoonhyuk Choi, Sae-Hong Cho, Beakcheol Jang