Llm

RSS

Sophos Insights

LLM

Exploit

vulnerability

Active Adversary

Pacific Rim

The vulnerability flood is here. Here’s what it means – and how to prepare

We can't control the pace of AI-driven vulnerability discovery, but we can control how fast we respond.

Threat Research

OpenClaw

LLM

penetration testing

Red Team

CISO

Sophos X-Ops

We let OpenClaw loose on an internal network. Here’s what it found

Following our article on the challenges posed by agentic AI, we gave OpenClaw access to one of our legacy networks

Threat Research

LLM

OpenClaw

CISO

risk

Sophos X-Ops

The OpenClaw experiment is a warning shot for enterprise AI security

Agentic AI promises a lot – but it also introduces more risk. Sophos’ CISO explores the challenges and how to address them

A computer hard disk on fire against a white background

Threat Research

Ransomware

Hive

Lockbit

BlackCat

LLM

Money Laundering

Laughter in the dark: Tales of absurdity from the cyber frontline and what they taught us

A photograph of a hand reaching out to lock a prison cell with a bunch of keys

AI Research

CAMLIS

Featured

jailbreak

LLM

salting

Sophos X-Ops

Locking it down: A new technique to prevent LLM jailbreaks

A salt shaker lying flat on a blue tabletop, with the lid off and salt spilling out on to the table

AI Research

CAMLIS

Featured

LLM

Sophos X-Ops

Getting salty with LLMs: SophosAI unveils new defense against jailbreaking at CAMLIS 2025

A hand holding a magnifying glass above several blocks containing pictures of triangles. The block directly under the magnifying glass is taller and has a larger triangle on it

Threat Research

anomaly detection

Black Hat

command line

Featured

LLM

Sophos X-Ops

Sophos AI at Black Hat USA ’25: Anomaly detection betrayed us, so we gave it a new job

A large toy robot holding the hand of a smaller one, on a white floor against a red-orange background

Threat Research

Featured

LLM

small models

Sophos AI

Sophos X-Ops

Small world: The revitalization of small AI models for cybersecurity

A row of white cubes on a blue background. The cubes contain checkmarks, with a yellow cube in the middle containing an alert symbol.

Threat Research

anomaly detection

black hat 2025

Featured

LLM

Sophos AI

Sophos X-Ops

SophosAI at Black Hat USA ’25: Anomaly detection betrayed us, so we gave it a new job

shutterstock_asset-generation-6dc4f763-f8a7-4dff-a56b-92736d8c8d6c-1_edited

AI Research

deepspeed

Featured

LLM

LLM tuning

DeepSpeed: a tuning tool for large language models

Flat,Line,Design,Website,Banner,Of,Learning,Process,,Brain,Process,

AI Research

AI Trojans

Featured

LLM

Sophos AI to present on how to defang malicious AI models at Black Hat Europe

Ai,Tech,,Businessman,Show,Virtual,Graphic,Global,Internet,Connect,Chatgpt

AI Research

AI Trojans

anti-phishing

CAMLIS

Featured

Google

LLM

small model machine learning

SophosAI team presents three papers on AI applied to cybersecurity at CAMLIS