Skip to content
Apart Research
Apart Research
Contact us
Sprint projectMar 23, 2026Washington DC, Europe, Iowa, Los Angeles

Hidden in Plain Sight: Representational Adversarial Steganography in Colluding LLMs

Vainateya Rangaraju, Srujana Medicherla, Denis Lim, Guillaume Zahnd, Anna Konovalenko, Igor Pereverzev · Team RASCAL

Submitted to AI Control Hackathon 2026. Sprint projects are early-stage work by participants, not Apart Research publications.

Read the report

Report: Hidden in Plain Sight: Representational Adversarial Steganography in Colluding LLMs

Open in a new tab (opens in new tab)
Code (opens in new tab)
Share

We investigate whether Large Language Models (LLMs) can develop representational steganography: the ability to encode and transmit hidden signals within internal representations that are not readily detectable by oversight mechanisms. We apply this to the threat models of deception and collusion in multi-agent settings. We show that this capability emerges under adversarial pressure, and discuss the robustness of our experiments, and what they might show for existing machine oversight regimes.

Reviews

Judging this Sprint?

Review this project

Your public critique appears on this page without your name. Your private critique is not published; only the Apart team reads it. If you agree below, we share your review with grantmaking.ai (opens in new tab) and the Transformative AI Fund so strong projects can be funded.

Not shown on this page.

Shown on this page, without your name.

Only the Apart team reads this, and funders if you agree below.

Share my name publicly on grantmaking.ai *
Share my private critique with funders *

How much would this matter for AI safety if it worked? How innovative is it? For scores of 4-5: is this actually new to the field, or replicating recent work?

Scoring guide
  1. 1Negligible. No clear problem addressed, or no meaningful novelty.
  2. 2Limited. Addresses a real problem but with a generic or well-trodden approach. Incremental at best.
  3. 3Moderate. Clear problem with a reasonable approach; some novelty in framing or method beyond routine application of existing tools.
  4. 4Significant. Important problem with an original approach, or identifies a neglected problem area. A valuable contribution others could build on.
  5. 5Exceptional. Tackles a critical AI safety problem with a genuinely novel approach, or opens a new research direction. Clear theory of change. You'd be excited to share this with researchers in the area.

How sound are methodology, implementation, and findings?

Scoring guide
  1. 1Seriously flawed. Methodology broken, results uninterpretable, or implementation doesn't work.
  2. 2Weak. Approach has significant gaps: missing validation, flawed experimental design, or incomplete implementation.
  3. 3Competent. Technically solid given the short duration. Methodology makes sense, results are interpretable, limitations acknowledged, work builds toward clear conclusions.
  4. 4Strong. Thorough methodology with convincing validation. Results clearly support conclusions. Immediately useful for future work.
  5. 5Exceptional. Ambitious scope executed rigorously. Surprising findings, novel methods, or unusually robust validation.

How clearly are work, findings, and impact potential communicated?

Scoring guide
  1. 1Incomprehensible. Cannot determine what the project is actually claiming or doing.
  2. 2Hard to follow. Key information buried, missing, or diluted by excessive length. Significant effort to extract main points.
  3. 3Clear enough. Can understand the problem, approach, and results without undue effort. Core content clearly present: problem, method, findings, limitations.
  4. 4Well presented. Easy to follow, well-structured, appropriate level of detail. Target audience would get it quickly.
  5. 5Exceptionally clear. A pleasure to read. Complex ideas made accessible. Could serve as a model for how to present this type of work.

  1. Interesting work on representational steganography for multi-agent control. But I have two main concerns:

    1. The threat model: it's not clear why two agents in the wild would share representations through an explicit latent channel; real multi-agent communication happens via text/APIs, so the setup feels contrived

    2. The evaluation - the key claim is that communication survives adversarial pressure from the monitor, but the available results mostly show Experiment 1 (communication without evasion), and ROC/safety curves would have been much more interpretable than point accuracies for telling the safety story about monitor evasion tradeoffs.

  2. A well-presented, technical implementation and exploration of steganography in a shared-activation space situation. The rank-8 constraint is a smart bottleneck. I thought the figures were very useful.

    The motivation of this felt like the notable weak point. Current multi-agent systems communicate through text and not through shared residual streams, so the practical relevance of this threat model isn't clear to me. This ultimately detracted from the underlying idea and the work - which I think were both quite good. Also, this result required deliberate trial-and-error training pressure, and did not arise spontaneously, which makes this a less pressing safety concern.

    I still think there are fruitful areas to explore here, if you wanted to take this further. There may be an argument to be made about multi-headed or mixture-of-experts architectures where components do share internal representations, and whether selection pressures in those settings could produce something analogous to your training dynamics. I'd be interested in your take on that!

    Read full reviewShow less

Cite this project

@misc{rangaraju2026hidden,
  title = {{Hidden in Plain Sight: Representational Adversarial Steganography in Colluding LLMs}},
  author = {Vainateya Rangaraju and Srujana Medicherla and Denis Lim and Guillaume Zahnd and Anna Konovalenko and Igor Pereverzev},
  year = {2026},
  month = mar,
  note = {Submitted to AI Control Hackathon 2026, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/hidden-in-plain-sight-representational-adversarial-steganography-in-colluding-llms-sekh}},
  url = {https://apartresearch.com/sprints/projects/hidden-in-plain-sight-representational-adversarial-steganography-in-colluding-llms-sekh}
}

More from AI Control Hackathon 2026

All 125 entriesBrowse all projects

Build something like this at the next Sprint

AI Collusion Research Sprint · Oct 23 - 25, 2026