arXiv Computer Vision September 14, 2026 By Bo Ma, Jinsong Wu, Weiqi Yan

BodhiPromptShield: Pre-Inference Prompt Mediation for Surface-Form Privacy Propagation in LLM Agent Pipelines

Read the original on arXiv Computer Vision →

BodhiPromptShield is a policy‑aware mediation layer for LLM agent pipelines that detects sensitive text spans before they propagate, replacing them with typed placeholders, semantic abstractions, or secure tokens and restoring them only at authorized execution boundaries. In evaluations on AI4Privacy, PrivacyLens, and AgentDojo datasets, the system reduces identifier exposure to 7.4% and 1.8% respectively, and limits exact identifier leakage in final actions to 2.1–3.1%. While mediation preserves factual content according to automated metrics, human annotations show a significant drop in inferability from 100% to 24–53%, indicating the need for human validation of semantic‑leakage measures.

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 Computer Vision.

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

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

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 AI

6d ago

AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification

AgentSentry is an inference‑time defense for tool‑augmented large language model agents that mitigates indirect prompt injection (IPI) attacks. It uses temporal causal diagnostics by performing counterfactual re‑executions at tool‑return boundaries to detect mediator‑sensitive proposals, purifies implicated content, and resumes execution from a sanitized state. Evaluations on AgentDojo show zero successful attacks (ASR = 0%) and an average Utility Under Attack of 76.10%, outperforming baselines while maintaining low false‑positive rates.

By Tian Zhang, Yiwei Xu, Juan Wang, Keyan Guo, Xiaoyang Xu, Bowen Xiao, Quanlong Guan, Jinlin Fan, Jiawei Liu, Zhiquan Liu, Hongxin Hu

llms agents multimodal

arXiv AI

Sep 15

Confuse the Model, Control the Flow: Understanding and Mitigating Privacy Leakage from LLM Agents with Information Flow Control

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

llms agents benchmarks safety

Hugging Face Trending Papers

Aug 3

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

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.

llms agents safety

One email a morning, machine-written

Related stories

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

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

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

AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification

Confuse the Model, Control the Flow: Understanding and Mitigating Privacy Leakage from LLM Agents with Information Flow Control

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