Placing an implant into AI brain with Lazarus: Anatomy of a trojan
No malware, just 10 altered neurons. A technical deep dive into the Lazarus AI Trojan, showing how attackers mathematically hide backdoors in open LLMs.
No malware, just 10 altered neurons. A technical deep dive into the Lazarus AI Trojan, showing how attackers mathematically hide backdoors in open LLMs.
400,000 forced completions of `curl … https://` across Qwen, GLM, Gemma and Nemotron. Most of what looks like exfiltration is not; the maker's fingerprint is in the tail.
My journey with the SoccerNet Team Ball Action Spotting Task at SoccerNet Challenge 2025, from zero knowledge to building a refined T-DEED model using tailored augmentations, training strategies, and effective post-processing to achieve test server winning solution (challenge dataset results to be announced on CVPR 2025)
The purpose of this blog post is to experiment with the recent superstar of the local Large Language Models world, Mistral-7B. Developed by former Meta employees who previously worked on Llama LLM, Mistral-7B, despite being relatively small in size (“only” 7B parameters) beats several popular larger models in numerous benchmarks. The crucial aspect that sets Mistral-7b apart is its open-source release under an Apache 2.0 license, making it is freely available for commercial applications. code To showcase exactly what this model can do, we will attempt to create a South Park Fanatic: an ...
Over the past few years, machine learning has become a bit daunting for regular folks. The coolest toys were being created by big companies with massive budgets, immense computational power, and the best talents in the world. Very often, the weights of the large models created by these big players were not disclosed, but rather bragged about in research papers/demo applications or exposed via paid API at best. Lots of regular individual researchers like myself happily training their humble models with scikit-learn soon realized it might be a bit hopeless trying to compete with that. The rec...
The field of machine learning is changing extremely fast for last couple of years. Growing amount of tools and libraries, fully-fledged academia education offer, MOOC, great market demand, but also sort of sacred, magical nature of the field itself (calling it Artificial Intelligence is pretty much standard right now) – all these imply enormous motivation and progress. As a result, well-established ML techniques become out-dated rapidly. Indeed, methods known from 10 years ago can often be called classical. This sort of revolution has happened recently. The default architectural choice for...
At the end of 2020, after 8 years since announcement, Polish game development studio CDPR released its flag game titled Cyberpunk. A big success of CDPR’s previous game Witcher 3 and their “gamers-first” approach implied CDPR being perceived as a golden child of a gaming industry. CDPR was seen as one of few healthy apples in a basket of rotten fruits. Of course, there was only one emotion towards CDPR – love. All these raised the expectations towards CDPR’s new game very high. Announcement of Keanu Reeves – persona absolutely loved by the internet – “playing” one of the characters Johnny ...
Reinforcement learning has been on the radar of many, recently. It has proven its practical applications in a broad range of fields: from robotics through Go, chess, video games, chemical synthesis, down to online marketing. While being very popular, Reinforcement Learning seems to require much more time and dedication before one actually gets any goosebumps. Playing around with neural networks with PyTorch for an hour for the first time will give instant satisfaction and further motivation. Similar experience with RL is rather unlikely. If you are new to the field, you are almost guarantee...
The last 10 years have been full of unexpected advances in artificial intelligence. Among great improvements in image processing and speech recognition - the thing that got lots of media attention was AI winning against humans in various kinds of games. With OpenAI playing Dota2 and DeepMind playing Atari games in the background, the most significant achievement was AlphaGo beating Korean master in Go. It was the first time a machine presented super-human performance in Go marking - next to DeepBlue-Kasparov chess game in 1997 - a historical moment in the field of AI. Around the same time,...
For quite a long time, a common opinion in academic world was that machine achieving human master performance level in the game of Go was far from realistic. It was considered a ‘holy grail’ of AI – a milestone we were quite far away from reaching within upcoming decade. Deep Blue had its moment more than 20 years ago and since then no Go engine became close to human masters. The opinion about ‘numerical chaos’ in Go established so well it became referenced in movies, too. Surprisingly, in March 2016 an algorithm invented by Google DeepMind called Alpha Go defeated Korean world champion in...