Daniel Lerch

PhD. Researcher in #Steganography and #Steganalysis. Interested in #Cryptography, #MachineLearning and #IoT.

[Daniel Lerch @Daniel_Lerch]

HStego 0.3, the hard-to-detect image #steganography tool, has been released. Now with graphical interface and standalone exectuables for Linux and Windows.

https://t.co/cfKGDwMalB

[Daniel Lerch @Daniel_Lerch]

HStego 0.6, the hard-to-detect image #steganography tool, has been released.

It uses S-UNIWARD and J-UNIWARD + Cost Polarization, with payload limits designed to reduce detectability.

https://t.co/cfKGDwMalB

#steganalysis #infosec #opensource

[Daniel Lerch @Daniel_Lerch]

CUING 2026 (Cyber Use of Information Hiding) is open for submissions!

📍 Linköping, Sweden
📅 August 24–27, 2026

Topics: steganography, covert channels, info hiding.

Submit your work!

🔗 https://t.co/gqRX3vKseH

#CFP #Cybersecurity #InfoHiding #ARES2026

[Carlos Santana @DotCSV]

🔴 ¡MODELOS OPENSOURCE de OPENAI!

OpenAI ha recordado de donde venía lo de 'open' y acaba de liberar sus nuevos modelos razonadores pensados para realizar tareas agénticas 🔥

> Un modelo de 20B para PC y portátiles
> Un modelo de 120B para datacenters y PCs high-end

Os cuento!

[Simpsons Quotes @Simpsons_tweets]

R.I.P. Ozzy Osbourne.

[sunny @thePiggsBoson]

The importance of stupidity in scientific research by Martin Schwartz (2008)

[Kevin Patrick Murphy @sirbayes]

I am pleased to announce a new version of my RL tutorial. Major update to the LLM chapter (eg DPO, GRPO, thinking), minor updates to the MARL and MBRL chapters and various sections (eg offline RL, DPG, etc). Enjoy!
https://t.co/SjMdabl0yW

[Valeriy M., PhD, MBA, CQF @predict_addict]

🎯 Tracking enemy aircraft with math? Enter the godfather of cybernetics Norbert Wiener.

During WWII, MIT mathematician Norbert Wiener (1894–1964) was tasked with a critical challenge: predict the future position of German bomber aircraft using only past radar observations.

📡 The result?

[The Nobel Prize @NobelPrize]

BREAKING NEWS
The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Chemistry with one half to David Baker “for computational protein design” and the other half jointly to Demis Hassabis and John M. Jumper “for protein structure prediction.”

[The Nobel Prize @NobelPrize]

BREAKING NEWS
The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”

[filipe @filicroval]

Esto es «Flipper ZERO»

Esto puede entrar en tu casa 💀.

Aquí hay algunos ejemplos LOCOS:

[Jordi Herrera @joancomarti]

We are offering a postdoc position in our research group in the field of cryptocurrencies and blockchain technologies. RT for maximum spread are welcome. https://t.co/EnUruJoVNL

[Diario de un picateclas @devruso]

¿Os acordáis de nuestro amigo Jia Tan, el prota de la historia de ayer?

Acompañadme en este pequeño hilo que cubre el drama de hoy v2 🧵⬇️

[Wojciech Mazurczyk @wmazurczyk]

And here another #stegomalware example - this time using JPEGs - the trend of using #steganography and other data hiding techniques in malware is rising... CC: @lucacaviglione

[The Verge @verge]

Google is embedding inaudible watermarks right into its AI generated music https://t.co/1g34WhiLr0

[BlockSerious @blockserious]

Language models can use steganography to hide their reasoning, study finds
In a new study, Redwood Research, a research lab for AI alignment, has unveiled that large language models (LLMs) can master “encoded reasoning,” a form of steganography. This intriguing phenomenon allows LLMs to subtly embed intermediate reasoning steps within their generated text in a way that is undecipherable to human readers.
More: https://t.co/dwlxzchtYJ

[Alfonso Muñoz, Phd @mindcrypt]

¿Conocías este tipo de técnicas? ¿Te parecen antiguas? Quizás ahora puedas entender mejor como un puñado de músicos engañaron al KGB... https://t.co/lvoqAxKBRq

[Daniel Lerch @Daniel_Lerch]

@collinsmuriuki_ A tip, use LSB matching instead of LSB replacement. Just as simple, much safer.

[Daniel Lerch @Daniel_Lerch]

Text steganography with ChatGPT.
https://t.co/59k5QQkCUs

[Daniel Lerch @Daniel_Lerch]

Esteganografía en texto con ChatGPT.
https://t.co/FxsGxs91n1

[PHD Comics @PHDcomics]

Scary