Locking it down: A new technique to prevent LLM jailbreaks
Many organizations are increasingly deploying large language models (LLMs) such as OpenAI’s GPT series, Anthropic’s Claude, Meta’s LLaMA, and various...
AI Research
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...
Enhancing Cybersecurity with Multimodal AI
A paper was presented by Sophos Principal Data Scientist Younghoo Lee at the Virus Bulletin conference in 2024, discussing SophosAI's...
ProfoundVelocity: a fine-tuning resource for vast linguistic models
Massive Linguistic Models (MLMs) hold the promise to mechanize and lessen the workloads of various kinds, such as those of...
Sophos Artificial Intelligence to showcase how to disarm malevolent AI models at Black Hat Europe
During this week's Black Hat Europe in London, Senior Data Scientist Tamás Vörös from SophosAI will be providing a 40-minute...
AI Team from SophosAI Introduces Three Papers on AI Implemented in Cybersecurity at CAMLIS
The event Applied Machine Learning in Information Security (CAMLIS) was conducted this week in Arlington, Virginia. One of the papers...
Political Coercion Using Extensive AI-Driven Disinformation and Precision-targeting
Within the current digitally interconnected society, the strategies used for political communication and misinformation are evolving into more intricate forms....
SophosAI speaking at Virus Bulletin ’24: Leveraging multimodal AI as a “sensory extension” for cybersecurity
During this week’s Virus Bulletin 2024 event in Dublin, Ireland, the principal data scientist at Sophos, Younghoo Lee, is set...
