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

arXiv: https://arxiv.org/abs/2601.14660 · HTML: https://mlsanity.com/paper/2601.14660/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 18 of its 30 references that are in the map.
- First posted on arXiv 21 Jan 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)
- LLM safety and security / [Prompt injection and agent security](https://mlsanity.com/safety/prompt-injection-and-agent-security/)

## Builds on (most cited first, 18 of 18)

- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- [AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models](https://mlsanity.com/paper/2310.04451/) (2023)
- [The Linear Representation Hypothesis and the Geometry of Large Language Models](https://mlsanity.com/paper/2311.03658/) (2023)
- [Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack](https://mlsanity.com/paper/2404.01833/) (2024)
- [SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal](https://mlsanity.com/paper/2406.14598/) (2024)
- [Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory](https://mlsanity.com/paper/2310.17884/) (2023)
- [PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action](https://mlsanity.com/paper/2409.00138/) (2024)
- [Are Sparse Autoencoders Useful? A Case Study in Sparse Probing](https://mlsanity.com/paper/2502.16681/) (2025)
- [Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning](https://mlsanity.com/paper/2405.12241/) (2024)
- [Detecting High-Stakes Interactions with Activation Probes](https://mlsanity.com/paper/2506.10805/) (2025)
- [Operationalizing Contextual Integrity in Privacy-Conscious Assistants](https://mlsanity.com/paper/2408.02373/) (2024)
- [Privacy in Action: Towards Realistic Privacy Mitigation and Evaluation for LLM-Powered Agents](https://mlsanity.com/paper/2509.17488/) (2025)
- [Breach By A Thousand Leaks: Unsafe Information Leakage in `Safe' AI Responses](https://mlsanity.com/paper/2407.02551/) (2024)
- [Unsupervised Concept Vector Extraction for Bias Control in LLMs](https://mlsanity.com/paper/2502.19721/) (2025)
- [Beyond Jailbreaking: Auditing Contextual Privacy in LLM Agents](https://mlsanity.com/paper/2506.10171/) (2025)
- [FRACTURED-SORRY-Bench: Framework for Revealing Attacks in Conversational Turns Undermining Refusal Efficacy and Defenses over SORRY-Bench (Automated Multi-shot Jailbreaks)](https://mlsanity.com/paper/2408.16163/) (2024)
- [On Surjectivity of Neural Networks: Can you elicit any behavior from your model?](https://mlsanity.com/paper/2508.19445/) (2025)

## Built on by (most cited first, 1 of 1)

- [When the Agent Becomes the Kernel: A Systematization of Security on the Path to AI-Native Operating Systems](https://mlsanity.com/paper/2609.23700/) (2026)

## Abstract (arXiv)

Agentic Large Language Models (LLMs) are models able to reason, plan, and execute tools over unstructured data. These abilities enable transformative applications in domains spanning personal assistants, financial, and legal domains, etc. While these systems can substantially improve productivity and service quality, effective agency typically requires access to sensitive personal or organizational information. However, this access introduces critical inference-time privacy risks, specifically regarding contextually appropriate information disclosure. While recent studies highlight the inability of agentic LLMs to consistently adhere to privacy norms, existing defenses often rely on auxiliary LLM-based monitors. However, these defenses are expensive and offer limited protection against attacks that are robust to semantic censorship. To contrast this background, this paper proposes a notion of privacy filters based on activation probing. We show that these filters are both computationally efficient and effective for both single-turn and multi-turn conversational settings. Furthermore, this work provides the first systematic investigation into probing model internals across a conversation trajectory, moving beyond static, single-prompt analysis to capture the evolving state of privacy-sensitive interactions, illustrating their applicability across contexts, attack styles, multiple base models, and challenging settings such as mosaic attacks, while providing nuanced insights into the nature of the discovered concepts and modular construction of probes.