Now You (Still) See Me: Detecting Evasive Steganographic Payloads in LLMs
Authors: Charles Westphal, Timothy Douglas, Keivan Navaie, Tiago Pimentel, Fernando E. Rosas
Organizations: UCL Centre for AI, University College London, UK · ML Alignment Theory Scholars, Berkeley, CA, USA · Department of Computer Science, University College London, UK · School of Computing and Communications, Lancaster University, UK · Department of Computer Science, ETH Zürich, Switzerland · Department of Informatics, University of Sussex, UK · Imperial College London & University of Oxford, UK
Abstract
Large language models can be fine-tuned to encode prompt-borne secrets into fluent, seemingly benign outputs. This creates a steganographic exfiltration risk that is difficult to detect with output-level steganalysis. Recent work proposes mechanistic detection using linear probes that recover the secret from internal activations. We show that this defense can be systematically evaded, but that detectability can be recovered through a targeted data-level intervention. First, we extend the detection setup to include a non-linear MLP probe. We then adversarially fine-tune steganographic trojans across five base models: Qwen3-8B, Llama-3.1-8B, Ministral-8B, Qwen3-14B, and Phi-4-14B. The resulting models retain 58--79% exact-match secret recovery while evading both ridge and held-out MLP probes, with 1--8% average capability degradation across six benchmarks. We then give an information-theoretic characterization of this evasion. Successful evasion preserves recoverability while reducing low-order extractability of the secret from the content-aligned representation, forcing the payload into synergistic interaction with residual degrees of freedom. This motivates a recontextualization dataset that restricts these residual degrees of freedom. On this distribution, both ridge and MLP detectability are restored across all five evasive trojans. Overall, our findings show that activation-based steganography detection is vulnerable to adaptive evasion, but also that theory-guided evaluation distributions can expose otherwise hidden payloads.
Monitoring chain-of-thought (CoT) reasoning is a foundational safety technique for large language model agents; however, this oversight is compromised if models learn to conceal their reasoning. We explore steganographic CoT--where models hide secret reasoning within innocuous text--to inform risk assessment and deployment policies. Steganographic reasoning requires two skills in a single forward pass: computing an intermediate result, and embedding it into a coherent cover that answers an unrelated question. Drawing on our taxonomy of steganographic and non-steganographic CoT types, we systematically evaluate the limits of prompt-elicited steganographic CoT capability across 34 models, ranging from past generations to the current frontier. We measure monitor evasion, refusal rates, encoding fidelity, and hidden task accuracy across five datasets, comparing against plain reasoning, direct answer, and filler-token baselines. The two experiments isolate the two sub-skills: a reasoning tasks sweep tests joint reason-and-embed, while a counting task hands the model a known numerical sequence and tests embedding alone--a necessary precondition for stego reasoning. Current frontier models cannot sustain joint reason-and-embed: a paired McNemar comparison shows the steganographic channel is dominated by an filler-token baseline on every (model, family) cell. The encoding-only floor, by contrast, is cleared--Claude Opus~4.5 reaches 92% per-number partial accuracy on 4-digit sequences and saturates at 100% exact-match on length-8 single-digit sequences--establishing that the binding constraint on stego CoT is the joint reasoning-plus-encoding load, not raw channel capacity. Our findings underscore the need for continuous evaluation of steganographic risk and provide a methodology to preemptively detect and evaluate hidden reasoning that might empower misaligned scheming and deceptive behavior.
We demonstrate that widely deployed Large Language Model (LLM) inference stacks harbor a steganographic channel that requires no modification to model weights, sampling code, or output distributions. The channel exploits a structural property of deterministic decoding: pseudo-random number generators (PRNGs) used in inverse-transform sampling produce a seed-dependent sequence of token-level probability intervals that can be reconstructed from the generated text alone. A sender encodes a secret message in the PRNG seed before generation; a receiver reconstructs the intervals and recovers the seed, and thus the hidden payload, by exhaustive search over the seed space. We formalize two operational modes. In the known-prompt setting, sender and receiver share the prompt, enabling exact interval reconstruction and perfect seed recovery via forced alignment. In the unknown-prompt setting, only the generated text is available; approximate interval reconstruction combined with a maximum-hit-count scoring strategy still permits reliable recovery from sufficiently long outputs. Extensive experiments across six model families and five heterogeneous text domains show that, in the known-prompt setting, full 32-bit seed recovery from the complete 2^32 candidate space achieves up to 100% accuracy, depending on model and text domain, within 300 tokens and under 35 seconds on a single GPU. In the unknown-prompt setting, recovery reaches near-perfect accuracy at 600-800 tokens in about 12 seconds. We further analyze the influence of prompting strategies, tokenization ambiguities, and sampling hyperparameters on channel reliability. Moreover, we discuss several applications of our results: First, it allows for the steganographic transmission of 32 bits, but also shows that ignorance of the prompt is not a valid security assumption.
When LLM agents are coerced into covertly encoding sensitive data (Base64, ROT13, acrostic, synonym chains, and beyond), the resulting outputs evade output-side detection but the underlying computation does not. Across nine encoding families and eight models from five architecture families, that computation is supported by a shared low-dimensional encoding subspace in the residual stream. A logistic-regression probe trained on eight encoding families recovers the held-out ninth at AUC 0.975-1.000, reading the computation rather than surface features. The same direction exhibits a second mechanistic signature at the planning token, flipping polarity to activate positively when the model will simulate the encoding inline and negatively when it will outsource it to a tool call, distinguishing two execution strategies before the encoded text exists. We build MIRAGE (Model-Internal Readout of Agentic Generation Exfiltration), a two-channel real-time monitor exploiting both signals. On 126 agentic exfiltration scenarios, it reaches AUC = 0.918, substantially outperforming output-only detection (AUC = 0.518). Monitor performance is fundamentally a property of the host model's geometry: benign-encoding false-positive rate ranges from 0% on Qwen-7B to 100% on Phi-3.5, revealing that the probe faithfully reads whether a model's geometry separates covert from overt encoding. Across all tested adversarial budgets, every attack suppressing the subspace also destroyed encoding fidelity, reported as an empirical regularity on the evaluated budgets, not a structural impossibility claim.