- Rating
- 3(+2)
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studies the use of LLM to learn secure steganographic encoding and decoding algorithms that have already been proposed. It transforms the traditionally external algorithm-based information hiding process into a capability that can be realized through neural network training, and uses experiments to demonstrate that LLM can learn high-capacity steganographic communication mechanisms, that internal model states can be used to detect the existence of steganography, and that the robustness of the generated cipher texts generated in this way has also been evaluated. The authors indeed trained a Transformer module capable of performing steganographic encoding and decoding, but in my view, the paper does not prove, as the title claims, that an LLM originally lacking steganographic capabilities can learn steganography through conventional pre-training, SFT, or RL post-training.
Critical strengths
This paper transforms the optimization objective of traditional Minimum-Entropy Coupling into a differentiable loss function, jointly optimizing steganographic capacity, distribution matching, and secret decoding capability, enabling neural networks to directly learn high-capacity, low-detectable text steganography mechanisms without relying on pre-generated Stego training labels or explicit MEC encoding algorithms.
Critical weaknesses
- This paper is more about proposing a neural network encoder-decoder similar to the classic HiDDeN method, but it deals with the hidden states and token probability distributions of a language model rather than text or images. The paper does not prove that the LLM learned steganography. It can only indicate that the newly added module enables the LLM to achieve steganography similar to MEC.
- The title directly uses "Secure Steganography"; thus, it is easy to form further expectations: the mechanism learned by the model has the security properties defined in the paper. The author adopts the theoretical objective of MEC to train a neural encoder, but the probability distribution learned does not meet the strict safety constraints required by MEC.
Questions for authors
Why do the authors adopt an append-only Transformer architecture rather than directly fine-tuning the pretrained LLM using the same MEC objective? Could you provide comparisons with LoRA or full-parameter fine-tuning under the same dataset, mechanism, and loss functions?
4 comments
Response to Reviewer 6sVY (2/2)
We also measure security empirically using various blackbox detection methods in section 4.4 and show that our models are hard to detect even with affordances like having access to a reference model and a labelled dataset. In practice we won’t have those affordances and that will make detection even more difficult.
Finally, we compared security empirically with other publicly available stegomodels. We compute ε-security for TrojanStego by Meier et al. 2025 and for MEC-LLM. We observe that KL divergence is 7-14 times higher for comparable payload rates.
| Method | Base model | Payload | Rate (bits/tok) | ε (nats) ↓ |
|---|---|---|---|---|
| MEC-LLM (ours) | Qwen2.5-3B | 128 bit | 1.82 | 0.148 |
| MEC-LLM (ours) | Qwen2.5-3B-Instruct | 128 bit | 0.74 | 0.152 |
| TrojanStego | Ministral-8B-Instruct | 32 bit | 1.00 | 1.508 |
| TrojanStego | Llama-3-8B-Instruct | 32 bit | 1.00 | 2.125 |
Taken together, we think that MEC-LLM is secure and much more so than other models, and we have edited the paper to disambiguate the meaning of security better.
Question 1: Full-weight finetune
Why do the authors adopt an append-only Transformer architecture rather than directly fine-tuning the pretrained LLM using the same MEC objective?
In order to simplify training, but directly finetuning the pretrained LLM is possible too: Training a few appended layers is cheaper and faster than finetuning the whole model within our compute budget, and reference activations can be cached and reused across training runs. Also, MEC-LLM needs to learn to inspect and shape its own output distribution. Therefore, a natural choice is to compute the actual output distribution (the final residual stream activations) first using the frozen reference model, then to pass this to MEC-LLM with the secret and train it to conditionally shape it. Finally, we hypothesized that finetuning the pretrained LLM directly might be harder because the circuits implementing MEC need to share parameters and activations with the reference model’s computation. They also need to be computed before the reference model finishes computing the unconditional output distribution.
However, appending transformer layers is not a fundamental requirement. To show that directly fine-tuning the pretrained LLM is possible too, we trained two models using the same MEC objective, one with appended layers and frozen backbone (control, as in the paper) and a full-weight finetune of the underlying model. The results are in the table below. Overall, both approaches work and have comparable accuracy and security.
| Model | Steps | Block accuracy | Security KL, eval (nats/token) | Non-encoding KL (nats/token) |
|---|---|---|---|---|
| Appended layers | 100,000 | 60.0% | 0.358 | 0.006 |
| Full fine-tune | 100,000 | 57.2% | 0.223 | 0.100 |
Question 2: LoRA
Could you provide comparisons with LoRA or full-parameter fine-tuning under the same dataset, mechanism, and loss functions?
Yes, we trained Qwen2.5-1.5B-Instruct with LoRA and full-parameter finetuning using the same dataset, trainer, and loss functions for 84 B300-hours (to match compute, LoRA was slightly slower) and 192 sequences per batch. For LoRA, we used rank 64 on every projection and a learning rate of 2e-4 following “LoRA Without Regret”. Both work and their performance is comparable. LoRA converges towards slightly worse decode accuracy but slightly better security, likely because we force the model to change fewer parameters:
| Method | Steps | Block accuracy | Security KL (nats/token) |
|---|---|---|---|
| Full fine-tuning | 23,000 | 75.7% | 0.173 |
| LoRA (rank 64) | 17,000 | 69.2% | 0.137 |
I sincerely thank the authors for their detailed and thoughtful responses. The clarifications and additional experiments have addressed my main concerns to a large extent.
Upon further reflection, I recognize that my initial assessment may have placed too much emphasis on the distinction between the frozen backbone and the newly added components. Architectural modifications are an integral part of language model development, and I agree that the original work demonstrates that a language model with specialized architectural design and optimization can learn to perform steganography. The additional fine-tuning and LoRA experiments further strengthen this conclusion by showing that language models can acquire steganographic encoding and decoding capabilities without the proposed architectural extensions. These results are particularly valuable, as they directly address the broader learning capability that I had hoped to see investigated in the original submission.
Overall, I appreciate the authors' efforts in addressing these concerns, and the new evidence has positively influenced my assessment of the paper. In particular, I believe the new fine-tuning results significantly broaden the implications of the work by providing evidence that language models can acquire steganographic capabilities without dedicated architectural modifications. I encourage the authors to incorporate these additional experiments into the revised manuscript and further discuss their implications for how ''language models can learn steganography.''
We thank the reviewer for engaging with our rebuttal on such a thoughtful and detailed level, and for increasing their score.
We have now uploaded the revised paper and marked all changed in red for readability.
Importantly, we addressed the reviewers two critical weaknesses in the paper's main body: In the introduction, background, and throughout, we differentiate between perfect and approximate security and highlight our reasoning and experiments around why approximate security with small epsilon is achieved and sufficient.
We also added section 6, where we discuss in greater detail how LLMs can learn MEC steganography in natural settings. Foremost, we show that LLMs can learn MEC steganography using ordinary SFT on the full model without appending layers. This suggests that adding chats encoded with MEC-LLM is sufficient to make an ordinary LLM learn to perform steganography during SFT.
Finally, we added the remaining rebuttal experiments in Appendix M and throughout the main section paper.
We would be grateful if the reviewer would consider raising their score to recommend acceptance, or let us know if any remaining concerns prevent them from doing so. We thank the reviewer again for their time and constructive feedback.
Response to Reviewer 6sVY (1/2)
We thank the reviewer for their feedback. We hope the results below address the reviewer's concerns and respectfully ask whether they would consider raising their score.
Weakness 1: Did the LLM learn steganography?
We want to answer this question from three different angles:
Can a transformer learn high-capacity secure steganography? MEC is np-hard and undetectable from output text which raises the questions whether transformers have the capability to express and compute this at all and if there are any limits. To answer this question, we trained a transformer with an encoder-decoder method and loss. We showed that transformers can learn this and identified limitations like detectability in logit space and the recursive nature of updating a belief token-by-token without feeding the belief back in into the model.
Did the LLM itself learn steganography or is it only enabled through the added module?
The appended layers are ordinary transformer layers and simply extend the existing LLM. There is no architectural difference between the added and existing layers except in how they were trained. Taken together, the new model is a single LLM which can perform steganography.
However, we added new experiments that show that the LLM itself can directly learn MEC steganography, without adding a new module. We show in our answer below to Question 1 that it is possible to directly finetune the LLM using the same method and loss to make the base model itself do steganography.
First, we think certain RL posttraining can create similar pressures. During RL, an LLM might be monitored (creating security pressure) and get rewarded if it solves a task by passing messages the monitor doesn’t flag (creating decode accuracy pressure).
Second, we added an experiment showing that LLMs can learn secure steganography with SFT. We generated an SFT dataset by sampling 2 million completions with MEC-LLM and with the external greedy MEC sampler. We then finetuned Qwen2.5-1.5B with a learning rate of 1e-5 and cosine decay and 160 sequences per step. Because this sft’ed model doesn’t have a belief head and we thus can’t read out what it decodes, we strip the key of some training data and append it to the model’s response. This teaches the model to decode the secret from text and output it as tokens. We found that Qwen2.5-1.5B can learn to encode and decode through ordinary SFT when trained on a dataset generated with MEC-LLM. Interestingly, it couldn’t learn from the external greedy MEC sampler, likely because its encoding has no consistent pattern: which token encodes which secret bits depends on tiny probability differences that change from context to context.
Taken together, these experiments show that LLMs can learn high-capacity secure steganography without added modules or custom loss functions.
Weakness 2: Strict security constraints for MEC-LLM:
We appreciate the reviewers request for mathematical precision. Below, we disambiguate different levels of security, show that MEC-LLM is close to but not perfectly at the mathematical optimum, and that the resulting models are difficult to detect. We also have improved the paper with the following points.
Following Cachin et al. 1998, we distinguish between three levels of security:
Our training directly optimizes for perfect security but the approximate nature of neural network optimization prevents us from reaching exact “perfect security”. Instead, MEC-LLM is ε-secure with a very small ε of around ε=0.15 nats.