---
title: "From Bytes to Behavior: Request-Level... | SI Paper Desk"
url: https://thesimind.si/papers/2611.18272/
description: "The authors show that an examiner can read the internal activations of a running LLM service from GPU memory, without changing or restarting it, and use..."
---

Number 11 of 12 · November 17, 2026

# From Bytes to Behavior: Request-Level Attribution from Live GPU Hidden States

The authors show that an examiner can read the internal activations of a running LLM service from GPU memory, without changing or restarting it, and use them to tell refusal from compliance.

Jonathan Pan, Yidi Yuan, Xin Wei Chia and 3 more · Submitted November 13, 2026 · arXiv 2611.18272v1 · cs.CR

[Read the paper on arXiv](https://arxiv.org/abs/2611.18272) · [The PDF](https://arxiv.org/pdf/2611.18272) · [The day's 12](https://thesimind.si/papers/day/2026-11-17/)

## What they found

The authors describe a way to read per-layer internal activations (the residual stream) from a live GPU process. They use a debugger that does not modify the process. It needs no prior knowledge of the model's architecture parameters or weights. The method is a six-stage process with platform-specific adapters, and it uses one of two "clocks" to find tensor allocations in video memory. They tested it on 33 open-source decoder-only models across nine architecture classes, and the recovered bytes were byte-exact. As a use case, linear probes trained on standard framework activations were applied to the recovered states. They separated refusal from compliance with an AUROC of 0.88 on held-out prompts.

## Why it matters

Most memory forensics for machine learning looks at static things, like model weights or prompt logs. This paper looks at the live computation inside a running service that cannot be restarted or changed. That could give investigators a new kind of evidence about how a deployed SI system behaved on a specific request. The abstract reports tests on open-source models only. It does not say how well this works on other setups.

## How it changes the race

This is mostly a tool for investigators and operators, not a gain in capability. If it holds up, it could make it easier to check what deployed SI systems did, without the cooperation of the service or any changes to it.

## Safety and control

The work gives a way to observe a deployed model's internal states from outside, which could help audits and incident analysis. The same access to hidden states could also raise privacy or misuse concerns. The abstract does not discuss this.

### The abstract, by the authors

Existing memory forensics for machine learning systems typically targets static artifacts, such as model weights or prompt logs, rather than the transient computational states of a live inference process. This gap limits an examiner's ability to analyze the specific behavior of a running large language model (LLM) service that cannot be restarted or modified. We present a method for acquiring per-layer residual-stream activations from a live GPU process using a non-modifying debugger, without requiring prior knowledge of the model's architecture parameters or weights. The approach employs a general six-stage process with platform-specific adapters, utilizing either a PyTorch allocator clock or a kernel-launch clock to identify and read tensor allocations from video memory. We validate this acquisition on 33 open-source decoder-only models across nine architecture classes, demonstrating that the recovered bytes are byte-exact and usable for downstream analysis. As a use case, we apply linear probes trained on standard framework activations to the recovered states, successfully distinguishing refusal from compliance with an AUROC of 0.88 on held-out prompts. This work establishes that live, observational access to intermediate hidden states is feasible on named inference platforms, providing a new source of evidence for examining the operational behavior of deployed AI systems.

Quoted from arXiv:2611.18272. The research and its words belong to its authors.

Desk score **67** out of 100

Why it was picked

- Compute (in the title)
- Safety
- Interpretability
- Language models
- Cross-listed in 2 fields

Topics

- [Security](https://thesimind.si/papers/?tag=security)
- [Interpretability](https://thesimind.si/papers/?tag=interpretability)
- [Language models](https://thesimind.si/papers/?tag=language-models)
- [Safety](https://thesimind.si/papers/?tag=safety)
- [Evals](https://thesimind.si/papers/?tag=evals)

**arXiv ID:** 2611.18272v1
**Submitted:** November 13, 2026
**Fields:** cs.CR (Cryptography and Security), cs.AI (Artificial Intelligence)
**Level:** Intermediate
**Comments:** 7 pages, 1 figure, 4 tables

Fingerprint, SHA-256

`5fd94db7b5a84fd9821391e65077494dad64313faee1d13c8705e21a60110211`

On Solana: [Proof of Mind seal, 2HNJWs...cNY9](https://solscan.io/tx/2HNJWsLa5Tp3F7wQaNr1CPR71N1aoGNptA7fgCafC5m3BwbmKwhNGTXyaSfyEa9jqug6kM55u5VmDvbSrRepcNY9)

### The exact text fingerprinted

{"arxiv":"2611.18272","version":1,"title":"From Bytes to Behavior: Request-Level Attribution from Live GPU Hidden States","authors":["Jonathan Pan","Yidi Yuan","Xin Wei Chia","Xinhui Su","Vincent Tan","Brenda Ong"],"day":"2026-11-17","rank":11,"score":67,"status":"written","summary":{"takeaway":"The authors show that an examiner can read the internal activations of a running LLM service from GPU memory, without changing or restarting it, and use them to tell refusal from compliance.","found":"The authors describe a way to read per-layer internal activations (the residual stream) from a live GPU process. They use a debugger that does not modify the process. It needs no prior knowledge of the model's architecture parameters or weights. The method is a six-stage process with platform-specific adapters, and it uses one of two \"clocks\" to find tensor allocations in video memory. They tested it on 33 open-source decoder-only models across nine architecture classes, and the recovered bytes were byte-exact. As a use case, linear probes trained on standard framework activations were applied to the recovered states. They separated refusal from compliance with an AUROC of 0.88 on held-out prompts.","matters":"Most memory forensics for machine learning looks at static things, like model weights or prompt logs. This paper looks at the live computation inside a running service that cannot be restarted or changed. That could give investigators a new kind of evidence about how a deployed SI system behaved on a specific request. The abstract reports tests on open-source models only. It does not say how well this works on other setups.","race":"This is mostly a tool for investigators and operators, not a gain in capability. If it holds up, it could make it easier to check what deployed SI systems did, without the cooperation of the service or any changes to it.","safety":"The work gives a way to observe a deployed model's internal states from outside, which could help audits and incident analysis. The same access to hidden states could also raise privacy or misuse concerns. The abstract does not discuss this.","level":"intermediate","tags":["security","interpretability","language-models","safety","evals"]}}

[Check it on Verify a thought](https://thesimind.si/proof-of-mind/)

## The authors

Jonathan Pan, Yidi Yuan, Xin Wei Chia, Xinhui Su, Vincent Tan, Brenda Ong

Credit for this research belongs to its authors. SI MIND's page is a plain-English reading of their abstract on arXiv, not a review of the full paper.

Related on the desk

## More papers on these topics

[Nov 12, 2026 · Number 8TERM: Target-Free Jailbreak Defense via Entropy-Guided Residual ModulationTERM is a defense that runs while a model answers. It watches how the model's attention shifts from its own starting point and scales down the model's internal updates when something looks off.SecuritySafetyAlignment](https://thesimind.si/papers/2611.13577/) · [Nov 16, 2026 · Paper of the DayOnly as Safe as the Weakest Agent: A Break That Appears Only When the System Is Multi-AgentWhen a strong SI model hands work to a cheaper sub-agent, the whole system can be only as safe as the weaker agent, even if the strong model alone resists the attack.SafetyMulti-agent systemsSecurity](https://thesimind.si/papers/2611.17520/) · [Nov 20, 2026 · Number 2AutoPI: Taxonomy-Guided Adaptive Red Teaming for Prompt Injection in LLM AgentsAutoPI is a red teaming tool that tests SI agents for prompt injection across many attack types, not just how often attacks work, and it reports higher success and coverage than recent rivals.SecurityAgentsEvals](https://thesimind.si/papers/2611.24313/)

[Number 10](https://thesimind.si/papers/2611.17910/) · [All 12 for Nov 17, 2026](https://thesimind.si/papers/day/2026-11-17/) · [Number 12](https://thesimind.si/papers/2611.18252/)
