arXiv AI
Aug 18
Synchronized Logit Steering: Real-world Steganography
arXiv:2608. 14697v1 Announce Type: new Abstract: Steganography in large language models offers a way to embed hidden messages within natural-sounding text.
Steganography Without Modification: Hidden Communication via LLM Seeds
arXiv:2606. 09135v1 Announce Type: cross Abstract: 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.
Related stories
arXiv AI
Jul 20
Hide and Seek in Embedding Space: Geometry-based Steganography and Detection in Large Language Models
arXiv:2601. 22818v2 Announce Type: replace-cross Abstract: Fine-tuned LLMs can covertly encode prompt secrets into outputs via steganographic channels.
arXiv Machine Learning
Jun 9
Now You (Still) See Me: Detecting Evasive Steganographic Payloads in LLMs
arXiv:2606. 09411v1 Announce Type: cross Abstract: Large language models can be fine-tuned to encode prompt-borne secrets into fluent, seemingly benign outputs.
arXiv AI
Aug 25
Adversarial Entropy Inflation Against Gumbel-Based Inference Verification
arXiv:2608.23375v1 Announce Type: cross Abstract: Gumbel-based inference verification bounds LLM weight exfiltration by only forgiving token choices that plausibly arise from honest GPU nondeterminis...
arXiv AI
Jun 9
Hiding in Plain Floats: Steganographic Carriers for Indirect Prompt and Content Injection
arXiv:2606. 08403v1 Announce Type: cross Abstract: Text-centered prompt-injection defenses assume that the malicious signal is visible in one of the inspected text views.
arXiv AI
3d ago
Security-Enhanced Seed-Based Weight Quantization for Large Language Models
arXiv:2609.38477v1 Announce Type: cross Abstract: Large language models (LLMs) incur substantial storage, memory-bandwidth and energy costs, motivating compact weight representations. Existing seed-b...
arXiv Machine Learning
Sep 11
CARTS: Contextual Autoregressive Rank Transcoding Steganography for Full-Capacity Keyed Text Encoding
The paper introduces CARTS, a steganographic method that uses autoregressive language models to encode a payload text into a stegotext of identical token length by preserving per‑position rank information across contexts. It provides a formal security analysis, proving exact correctness under deterministic model assumptions, and defines key security notions such as context search, key collisions, message equivocation, and non‑commutativity of encoding maps. Empirical tests on Llama 3 8B confirm perfect payload recovery, no random key collisions, and no commuting key pairs, indicating resistance to the studied attack vectors.
arXiv Computer Vision
Sep 22
Style as Cover: Deep Image Steganography via Stylized Transmission
arXiv:2609.22392v1 Announce Type: new Abstract: Image steganography hides secret message within normal images, with most existing works relying on cover-preserving transmission. However, such a parad...
arXiv Computation and Language
Sep 1
A Comprehensive Survey on Linguistic Steganography: Methods, Countermeasures, Evaluation, and Challenges
This survey reviews 148 linguistic steganographic methods, 60 countermeasures, 23 evaluation metrics, and 9 open challenges, providing taxonomies, reviews, and adoption analyses. It identifies five paradigm shifts brought by large language models: moving from covertext modification to prompt-only generation, from heuristic to provable security, from white-box symmetric models to black-box or asymmetric access, from security-centric designs to joint optimization, and from text-quality concerns to engineering issues. The paper aims to serve as a reference and roadmap for practical and responsible linguistic steganography in the LLM era.
arXiv AI
Aug 7
Text Steganography with Dynamic Codebook and Multimodal Large Language Model
arXiv:2604. 20269v2 Announce Type: replace-cross Abstract: With the popularity of the large language models (LLMs), text steganography has achieved remarkable performance.
arXiv AI
Jul 7
NEST: Nascent Encoded Steganographic Thoughts
arXiv:2602. 14095v2 Announce Type: replace Abstract: 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.
arXiv Computer Vision
3d ago
Feature-Aware Token Attack for Compression-Triggered Stealthy Failures in Large Vision-Language Models
arXiv:2609.39134v1 Announce Type: new Abstract: Visual-token compression improves the efficiency of large vision-language models, but can expose failures that full-token evaluation misses. We study a...