mlsanityData to 7 Oct 2026

Excuse me, sir? Your language model is leaking (information)

arXiv 2401.10360 ↗First posted 18 Jan 2024cs.CR cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

We introduce a cryptographic method to hide an arbitrary secret payload in the response of a Large Language Model (LLM). A secret key is required to extract the payload from the model's response, and without the key it is provably impossible to distinguish between the responses of the original LLM and the LLM that hides a payload. In particular, the quality of generated text is not affected by the payload. Our approach extends a recent result of Christ, Gunn and Zamir (2023) who introduced an undetectable watermarking scheme for LLMs.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 12 of its 32 references that are in the map. First posted on arXiv 18 Jan 2024.

Builds on

12 of 32 references.

References · 12

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  2. 2023A Watermark for Large Language Modelscited by 667
  3. 2023Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defensecited by 401
  4. 2023Can AI-Generated Text be Reliably Detected?cited by 372
  5. 2023Undetectable Watermarks for Language Modelscited by 208
  6. 2020Automatic Detection of Machine Generated Text: A Critical Surveycited by 160
  7. 2020Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hidingcited by 121
  8. 2023On the Possibilities of AI-Generated Text Detectioncited by 88
  9. 2023Three Bricks to Consolidate Watermarks for Large Language Modelscited by 80
  10. 2023Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Modelscited by 77
  11. 2022Perfectly Secure Steganography Using Minimum Entropy Couplingcited by 42
  12. 2015Maximal Noise in Interactive Communication over Erasure Channels and Channels with Feedbackcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 3; 2026: 4.

11 papers.

  1. 2024Pseudorandom Error-Correcting Codescited by 40
  2. 2024Watermarking Language Models for Many Adaptive Userscited by 16
  3. 2024Edit Distance Robust Watermarks via Indexing Pseudorandom Codescited by 12
  4. 2025StealthInk: A Multi-bit and Stealthy Watermark for Large Language Modelscited by 11
  5. 2024Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language Modelscited by 2
  6. 2025Key-Conditioned Orthonormal Transform Gating (K-OTG): Multi-Key Access Control with Hidden-State Scrambling for LoRA-Tuned Modelscited by 1
  7. 2026MirrorMark: Generalizable Mirrored Sampling for Multi-bit LLM Watermarkingcited by 1
  8. 2025An LLM Framework For Cryptography Over Chat Channelscited by 0
  9. 2026WorldCup Sampling for Multi-bit LLM Watermarkingcited by 0
  10. 2026Codetta: High-Capacity, Keyless, and Undetectable Multi-Agent Collusioncited by 0
  11. 2026Hidden Reasoning Must Leak, but Need Not Be Readable: Fundamental Opportunities and Limits for Chain-of-Thought Monitoringcited by 0