Hugging Face Trending Papers August 3, 2026

MNC: Scope-Bound Semantic Declassification for Private LLM-Agent Communication

Read the original on Hugging Face Trending Papers →

Multi-agent large language model (LLM) systems can expose protected state through internal messages, tool arguments, logs, and persistent memory even when their public outputs appear innocuous. Existing privacy prompts, redaction methods, and source-level access controls restrict surface content or data access, but do not specify what a legitimately informed agent should disclose or how that disclosure may be reused downstream.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI

Jun 26

Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents

arXiv:2606. 26627v1 Announce Type: cross Abstract: Large language model agents increasingly query databases, search document collections, call external APIs, remember past interactions, and act on a user's behalf.

By Nada Lahjouji, Ashwin Gerard Colaco

llms rag agents benchmarks safety data-engineering

arXiv AI

Jul 2

NeuroFilter: Activation-Based Guardrails for Privacy-Conscious LLM Agents

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

llms agents safety

arXiv AI

Jun 29

ToolPrivacyBench: Benchmarking Purpose-Bound Privacy in Tool-Using LLM Agents

arXiv:2606. 28061v1 Announce Type: cross Abstract: Large language models (LLMs) have increasingly moved from standalone text generation systems to agents that invoke external tools, access environments, and execute multi-step tasks.

By Shijing Hu, Liang Liu, Zhu Meng, Zhicheng Zhao

llms rag agents benchmarks safety

arXiv Machine Learning

Aug 5

DP-MemView: A Memory Interface for Attribute-Level Transcript Privacy in Long-Term LLM Agents

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

llms agents benchmarks safety

arXiv AI

Jun 2

PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say

arXiv:2606. 00152v1 Announce Type: cross Abstract: LLM-based agents are rapidly advancing, autonomously invoking external tools to complete multi-step tasks for users.

By Mingxuan Zhang, Jiahui Han, Dadi Guo, Songze Li, Guanchu Wang, Na Zou, Dongrui Liu, Xia Hu

llms agents benchmarks safety

arXiv AI

Jul 9

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents

arXiv:2607. 06595v1 Announce Type: cross Abstract: Personal AI agents powered by large language models can reason and act using available tools to access emails, manage calendars, and push code to remote repositories, all with minimal oversight.

By George Torres, Sharad Shrestha, Satyajayant Misra

llms agents benchmarks

Related stories

Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents

NeuroFilter: Activation-Based Guardrails for Privacy-Conscious LLM Agents

ToolPrivacyBench: Benchmarking Purpose-Bound Privacy in Tool-Using LLM Agents

DP-MemView: A Memory Interface for Attribute-Level Transcript Privacy in Long-Term LLM Agents

PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents