Many organizations are increasingly deploying large language models (LLMs) such as OpenAI’s GPT series, Anthropic’s Claude, Meta’s LLaMA, and various models from DeepSeek, with minimal customization. This widespread reuse leads […]
Continue Reading-
Getting salty with LLMs: SophosAI unveils new defense against jailbreaking at CAMLIS 2025
Scientists from the SophosAI team will present their research at the upcoming Conference on Applied Machine Learning in Information Security (CAMLIS) in Arlington, Virginia. On October 23, Senior Data Scientist […]
Continue Reading -
Sophos AI at Black Hat USA ’25: Anomaly detection betrayed us, so we gave it a new job
Following on from our preview, here’s Ben Gelman and Sean Bergeron’s research on enhancing command line classification with benign anomalous data Contact us today for more information about SOPHOS cyber […]
Continue Reading -
Small world: The revitalization of small AI models for cybersecurity
Sophos X-Ops explores why larger isn’t always better when it comes to solving security challenges with AI Contact us today for more information about SOPHOS cyber security solutions
Continue Reading -
SophosAI at Black Hat USA ’25: Anomaly detection betrayed us, so we gave it a new job
Sophos’ Ben Gelman and Sean Bergeron will present their research on enhancing command line classification with benign anomalous data at Las Vegas Contact us today for more information about SOPHOS […]
Continue Reading -
DeepSpeed: a tuning tool for large language models
SophosAI’s framework for upgrading the performance of LLMs for cybersecurity tasks (or any other specific task) is now open source. Contact us today for more information about SOPHOS cyber security […]
Continue Reading -
Sophos AI to present on how to defang malicious AI models at Black Hat Europe
“LLMbotomy” research reveals how Trojans can be injected into Large Language Models, and how to disarm them. Contact us today for more information about SOPHOS cyber security solutions
Continue Reading -
SophosAI team presents three papers on AI applied to cybersecurity at CAMLIS
On October 24 and 25, SophosAI presents ideas on how to use models large and small—and defend against malignant ones. Contact us today for more information about SOPHOS cyber security […]
Continue Reading -
Cybercriminals can’t agree on GPTs
Despite concern over illicit applications of ChatGPT and similar models, Sophos X-Ops’ exploration of cybercrime forums suggests many threat actors are still skeptical – and wrestling with the same issues […]
Continue Reading
You must be logged in to post a comment.