Inside the AI Red Teaming CTF: What 200+ players taught us about breaking and defending LLMs

In our paper, Breaking Guardrails, Facing Walls, we analyzeai_gon3_rogu3, a 10‑day AI red teaming CTF co-run…

How 11,000+ investigators cracked the case in Holmes, HTB’s defensive CTF

Great job, detectives! We have wrapped up our first-ever all-blue CTF, and there’s a ton we’d…

Board-ready cyber resilience: How to track and prove readiness

Every CISO out there knows the awkward silence that follows the question: “But how can we…

The AI Fix #73: Google Gemini is a gambling addict, and how to poison an AI

In episode 73 of The AI Fix, AI now writes more web content than humans and…

Smashing Security podcast #440: How to hack a prison, and the hidden threat of online checkouts

A literal insider threat: we head to a Romanian prison where “self-service” web kiosks allowed inmates…

The AI Fix #74: AGI, LLM brain rot, and how to scam an AI browser

In episode 74 of The AI Fix, we meet Amazon’s AI-powered delivery glasses, an AI TV…

Mitre Says Funding Set To Expire For Its Work On Crucial Vulnerability Program

Mitre confirmed that federal funding will run out Wednesday for its central role in operating the…

SOC Analysts – Reimagining Their Role Using AI

The job of a SOC analyst has never been easy. Faced with an overwhelming flood of…

HPE Investigating Breach Claims Involving Source Code: Report

Hewlett Packard Enterprise acknowledged it is investigating claims by a threat actor that reportedly involve theft…

Compromised AWS Keys Abused in Codefinger Ransomware Attacks

A threat actor has been observed abusing compromised AWS keys to encrypt data in S3 buckets…