RSS
Threat Research
AI
LLM
OpenClaw
CISO
risk
Sophos X-Ops
The OpenClaw experiment is a warning shot for enterprise AI security
Ransomware
Hive
Lockbit
BlackCat
Money Laundering
Laughter in the dark: Tales of absurdity from the cyber frontline and what they taught us
AI Research
CAMLIS
Featured
jailbreak
salting
Locking it down: A new technique to prevent LLM jailbreaks
Getting salty with LLMs: SophosAI unveils new defense against jailbreaking at CAMLIS 2025
anomaly detection
Black Hat
command line
Sophos AI at Black Hat USA ’25: Anomaly detection betrayed us, so we gave it a new job
small models
Sophos AI
Small world: The revitalization of small AI models for cybersecurity
black hat 2025
SophosAI at Black Hat USA ’25: Anomaly detection betrayed us, so we gave it a new job
deepspeed
LLM tuning
DeepSpeed: a tuning tool for large language models
AI Trojans
Sophos AI to present on how to defang malicious AI models at Black Hat Europe