The new HTTPS anomaly detection module in Slips builds per-host adaptive baselines in traffic time, then detects deviations at two levels: per-flow (for bytes to known servers) and per-hour (for host behavior like new servers, unique servers, JA3 changes, and flow volume). It uses online statistics and z-scores for transparent scoring, plus controlled adaptation states (training_fit, drift_update, suspicious_update) to keep learning while reducing poisoning risk.
The result is explainable, operational evidence in clear human text: what changed, confidence, and why it is anomalous.
Our research identifies sixteen fundamental principles of biological immunity and translates them into cybersecurity defense architectures that emphasize multi-dimensional coordination over single- point tactics.
We are pleased to announce the publication of our latest paper, “Building adaptive and transparent cyber agents with local language models,” in the Journal of Expert Systems with Applications.
Can a Raspberry Pi 5 run Large Language Models? In this post, we share the results of our experiments, analyzing how LLMs perform on this low-cost hardware and exploring the challenges and performance trade-offs.
The complete automation of cyber-attacks has become one of the areas of greatest interest since the introduction of Large Language Models (LLMs) to the public. The creation of attacking LLM agents that can act independently is among the most popular options.
In this blog, we introduce a brand-new agent: ARACNE. We also share the results of attack tests and what they mean in terms of the agent’s current capabilities.
Since the start of the Stratosphere Laboratory more than 11 years ago, we have always struggled to fund our free software development projects that were aimed at helping the privacy and security of the Internet. And this is where the NLnet foundation came to help us.
At Stratosphere actively use Yara Rules to identify and acquire samples, fresh or old, from specific threats and campaigns. We have published a repository with the rules we have created and used so far. The rules were separated in categories: malware, protocols and tools.
