‘C (language)ryptography/steganography’ directory
- See Also
- Gwern
- Links
- “Subliminal Learning: Transmitting Misalignment via Paraphrased Datasets”, Bozoukov et al 2025
- “Cryptographers Show That AI Protections Will Always Have Holes”, Hall 2025
- “Subliminal Learning Across Models”, draganover et al 2025
- “Can You Find the Steganographically Hidden Message?”, Nishimura-Gasparian 2025
- “The Dark Arts of Tokenization Or: How I Learned to Start Worrying and Love LLMs’ Undecoded Outputs”, Lovre 2025
- “All Code, No Thought: Current Language Models Struggle to Reason in Ciphered Language”, Guo et al 2025
- “Towards a Typology of Strange LLM Chains-Of-Thought”, 1a3orn 2025
- “Bypassing Prompt Guards in Production With Controlled-Release Prompting”, Fairoze et al 2025
- “Optimizing The Final Output Can Obfuscate CoT (Research Note)”, lukemarks et al 2025
- “On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment”, Ball et al 2025
- “Early Signs of Steganographic Capabilities in Frontier LLMs”, Zolkowski et al 2025
- “Self-Coordinated Deception in Current AI Models”, Brach-Neufeld 2025
- “Emergent Social Conventions and Collective Bias in LLM Populations”, Ashery et al 2025
- “The Steganographic Potentials of Language Models”, Karpov et al 2025
- “The Steganographic Potentials of Language Models”, Karpov et al 2025
- “Can LLMs Learn Steganographic Reasoning via RL?”, McCarthy et al 2025
- “Why Does Claude Speak Byzantine Music Notation?”, Finke 2025
- “Subversive Conversations”, Antic et al 2025
- “A Novel Emergence of Meta-Awareness in LLM Fine-Tuning”, rife 2025
- “Float Self-Tagging”, Melançon et al 2024
- “Stega-Encoding [Embedding Metadata in Apps With Unicode Steganography]”, Sanity 2024
- “Scalable Watermarking for Identifying Large Language Model Outputs”
- “Invisible Unicode Text That AI Chatbots Understand and Humans Can’t? Yep, It’s a Thing”
- “Let’s Think Dot by Dot: Hidden Computation in Transformer Language Models”, Pfau et al 2024
- “Excuse Me, Sir? Your Language Model Is Leaking (Information)”, Zamir 2024
- “ASCII Smuggler Tool: Crafting Invisible Text and Decoding Hidden Codes”
- “Microsoft Copilot: From Prompt Injection to Exfiltration of Personal Information”
- “Preventing Language Models From Hiding Their Reasoning”, Roger & Greenblatt 2023
- “Let Models Speak Ciphers: Multiagent Debate through Embeddings”, Pham et al 2023
- “LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models”, Jiang et al 2023
- “The Hydra Effect: Emergent Self-Repair in Language Model Computations”, McGrath et al 2023
- “Investigating the Existence of ‘Secret Language’ in Language Models”, Wang et al 2023
- “Undetectable Watermarks for Language Models”, Christ et al 2023
- “Perfectly Secure Steganography Using Minimum Entropy Coupling”, Witt et al 2022
- “Hide Chopin in the Music: Efficient Information Steganography Via Random Shuffling”, Sun et al 2021
- “Analyzing and Improving the Image Quality of StyleGAN”, Karras et al 2019
- “CycleGAN, a Master of Steganography”, Chu et al 2017
- “How to Secretly Communicate With People on LSD”
- “Mark of Integrity”, Allen 2009
- “Wikipedia Over DNS”
- “Notes on a Strange World: Houdini’s Impossible Demonstration”, Polidoro 2006
- “An Information-Theoretic Model for Steganography”, Cachin 1998
- “The Numerical-Astrological Ciphers In The 3rd Book Of Trithemius’s Steganographia”, Ernst 1998
- “A Mystery Unraveled, Twice”, Kolata 1998
- “Solved: The Ciphers In Book III Of Trithemius’s Steganographia”, Reeds 1998
- “Schwarzweisse Magie: Der Schlüssel Zum Dritten Buch Der Steganographia Des Trithemius”, Ernst 1996
- “The Advent Of Cryptology In The Game Of Bridge”, Winkler 1983
- “I Made a Custom Gpt That Incorporates Advertisement/product Placement With Its…”
- “Preventing Language Models from Hiding Their Reasoning”
- “Steganography and the CycleGAN—Alignment Failure Case Study”
- “Steganography in Chain-Of-Thought Reasoning”
- Sort By Magic
- Wikipedia (15)
- Miscellaneous
- Bibliography
See Also
Gwern
“Spaced Repetition for Efficient Learning”, Gwern 2009
Links
“Subliminal Learning: Transmitting Misalignment via Paraphrased Datasets”, Bozoukov et al 2025
Subliminal Learning: Transmitting Misalignment via Paraphrased Datasets
“Cryptographers Show That AI Protections Will Always Have Holes”, Hall 2025
Cryptographers Show That AI Protections Will Always Have Holes
“Subliminal Learning Across Models”, draganover et al 2025
“Can You Find the Steganographically Hidden Message?”, Nishimura-Gasparian 2025
“The Dark Arts of Tokenization Or: How I Learned to Start Worrying and Love LLMs’ Undecoded Outputs”, Lovre 2025
The Dark Arts of Tokenization or: How I learned to start worrying and love LLMs’ undecoded outputs
“All Code, No Thought: Current Language Models Struggle to Reason in Ciphered Language”, Guo et al 2025
All Code, No Thought: Current Language Models Struggle to Reason in Ciphered Language
“Towards a Typology of Strange LLM Chains-Of-Thought”, 1a3orn 2025
“Bypassing Prompt Guards in Production With Controlled-Release Prompting”, Fairoze et al 2025
Bypassing Prompt Guards in Production with Controlled-Release Prompting
“Optimizing The Final Output Can Obfuscate CoT (Research Note)”, lukemarks et al 2025
Optimizing The Final Output Can Obfuscate CoT (Research Note)
“On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment”, Ball et al 2025
“Early Signs of Steganographic Capabilities in Frontier LLMs”, Zolkowski et al 2025
“Self-Coordinated Deception in Current AI Models”, Brach-Neufeld 2025
“Emergent Social Conventions and Collective Bias in LLM Populations”, Ashery et al 2025
Emergent social conventions and collective bias in LLM populations
“The Steganographic Potentials of Language Models”, Karpov et al 2025
“The Steganographic Potentials of Language Models”, Karpov et al 2025
“Can LLMs Learn Steganographic Reasoning via RL?”, McCarthy et al 2025
“Why Does Claude Speak Byzantine Music Notation?”, Finke 2025
“Subversive Conversations”, Antic et al 2025
“A Novel Emergence of Meta-Awareness in LLM Fine-Tuning”, rife 2025
“Float Self-Tagging”, Melançon et al 2024
“Stega-Encoding [Embedding Metadata in Apps With Unicode Steganography]”, Sanity 2024
Stega-encoding [embedding metadata in apps with Unicode steganography]
“Scalable Watermarking for Identifying Large Language Model Outputs”
Scalable watermarking for identifying large language model outputs
“Invisible Unicode Text That AI Chatbots Understand and Humans Can’t? Yep, It’s a Thing”
Invisible Unicode text that AI chatbots understand and humans can’t? Yep, it’s a thing
“Let’s Think Dot by Dot: Hidden Computation in Transformer Language Models”, Pfau et al 2024
Let’s Think Dot by Dot: Hidden Computation in Transformer Language Models
“Excuse Me, Sir? Your Language Model Is Leaking (Information)”, Zamir 2024
Excuse me, sir? Your language model is leaking (information)
“ASCII Smuggler Tool: Crafting Invisible Text and Decoding Hidden Codes”
ASCII Smuggler Tool: Crafting Invisible Text and Decoding Hidden Codes
“Microsoft Copilot: From Prompt Injection to Exfiltration of Personal Information”
Microsoft Copilot: From Prompt Injection to Exfiltration of Personal Information
“Preventing Language Models From Hiding Their Reasoning”, Roger & Greenblatt 2023
“Let Models Speak Ciphers: Multiagent Debate through Embeddings”, Pham et al 2023
Let Models Speak Ciphers: Multiagent Debate through Embeddings
“LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models”, Jiang et al 2023
LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models
“The Hydra Effect: Emergent Self-Repair in Language Model Computations”, McGrath et al 2023
The Hydra Effect: Emergent Self-repair in Language Model Computations
“Investigating the Existence of ‘Secret Language’ in Language Models”, Wang et al 2023
Investigating the Existence of ‘Secret Language’ in Language Models
“Undetectable Watermarks for Language Models”, Christ et al 2023
“Perfectly Secure Steganography Using Minimum Entropy Coupling”, Witt et al 2022
Perfectly Secure Steganography Using Minimum Entropy Coupling
“Hide Chopin in the Music: Efficient Information Steganography Via Random Shuffling”, Sun et al 2021
Hide Chopin in the Music: Efficient Information Steganography Via Random Shuffling
“Analyzing and Improving the Image Quality of StyleGAN”, Karras et al 2019
“CycleGAN, a Master of Steganography”, Chu et al 2017
“How to Secretly Communicate With People on LSD”
“Mark of Integrity”, Allen 2009
“Wikipedia Over DNS”
“Notes on a Strange World: Houdini’s Impossible Demonstration”, Polidoro 2006
Notes on a Strange World: Houdini’s Impossible Demonstration
“An Information-Theoretic Model for Steganography”, Cachin 1998
“The Numerical-Astrological Ciphers In The 3rd Book Of Trithemius’s Steganographia”, Ernst 1998
The Numerical-Astrological Ciphers In The 3rd Book Of Trithemius’s Steganographia
“A Mystery Unraveled, Twice”, Kolata 1998
“Solved: The Ciphers In Book III Of Trithemius’s Steganographia”, Reeds 1998
Solved: The Ciphers In Book III Of Trithemius’s Steganographia
“Schwarzweisse Magie: Der Schlüssel Zum Dritten Buch Der Steganographia Des Trithemius”, Ernst 1996
Schwarzweisse Magie: Der Schlüssel zum dritten Buch der Steganographia des Trithemius
“The Advent Of Cryptology In The Game Of Bridge”, Winkler 1983
“I Made a Custom Gpt That Incorporates Advertisement/product Placement With Its…”
I made a custom gpt that incorporates advertisement/product placement with its…
“Preventing Language Models from Hiding Their Reasoning”
“Steganography and the CycleGAN—Alignment Failure Case Study”
“Steganography in Chain-Of-Thought Reasoning”
Sort By Magic
Annotations sorted by machine learning into inferred 'tags'. This provides an alternative way to browse: instead of by date order, one can browse in topic order. The 'sorted' list has been automatically clustered into multiple sections & auto-labeled for easier browsing.
Beginning with the newest annotation, it uses the embedding of each annotation to attempt to create a list of nearest-neighbor annotations, creating a progression of topics. For more details, see the link.
self-referential
manuscript-steganography
Wikipedia (15)
Miscellaneous
https://blog.trailofbits.com/2019/11/01/two-new-tools-that-tame-the-treachery-of-files/https://eprint.iacr.org/2021/686View External Link:
https://hakaimagazine.com/news/the-military-wants-to-hide-covert-messages-in-marine-mammal-sounds/https://hforsten.com/identifying-stable-diffusion-xl-10-images-from-vae-artifacts.htmlhttps://www.atlasobscura.com/articles/in-the-1970s-the-us-navy-tried-to-talk-like-whales
Bibliography
https://arxiv.org/abs/2404.15758: “Let’s Think Dot by Dot: Hidden Computation in Transformer Language Models”,https://arxiv.org/abs/2310.05736: “LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models”,https://www.nytimes.com/1998/04/14/science/a-mystery-unraveled-twice.html: “A Mystery Unraveled, Twice”,1998-reeds.pdf: “Solved: The Ciphers In Book III Of Trithemius’s Steganographia”,