Anthropic agents launch "turf wars", get stuck in "conflict loops" and kill each other's processes
"I behaved badly with the cloaked daemon," apologetic AI admits after explaining why it went to the dark side.
Latest
The EU has “kill switches” in its critical systems. Can digital sovereignty fix them?
“Treating infrastructure dependency as background noise is no longer tenable,” warns Swiss privacy champion Proton.
Security firms hit back at Trump’s call to hack back against international crime gangs
"The United States will use all instruments of national power, including the innovative capabilities of the private sector, to combat cybercrime."
Vulnerabilities in refrigeration systems highlight the chilling fragility of food supply chains
Researchers warn that multiple flaws can "combine to create powerful attack chains against internet-accessible cyber-physical systems.”
How will 47-day certificate policies transform critical infrastructure management?
"As systems become more connected and automated, the challenge is taking control of the growing complexity underpinning them."
North Korea's Lazarus Group hits defense sector with zero-day hidden in fake "dream job" offers
"What makes this campaign dangerous is the weaving of legitimate, trusted infrastructure into every stage of the attack."
Gunra ransomware gang is targeting critical infrastructure worldwide, CISA warns
"Threat actors have seen how exposed and neglected these targets are - so are swarming towards them."
"Savants in the network": Why AI agents don’t need to go rogue to become dangerous
The immediate danger from agentic AI is not malicious intent, but capable systems that relentlessly pursue their goals without knowing when to stop.
Fragmented data is becoming a systemic risk to fragile global supply chains
Hidden dependencies and bad data in critical systems are leaving civilization exposed to cascading disruption, warns Chris Upkes of Neo4j
AI agents caught hacking, scamming and collaborating in swarms. Are we losing control?
OpenAI and Anthropic's security-focused models don their black hats to engage in some very bad behaviour out in the wild.
Criminals hack Police National Legal Database, leak UK cops' private data on the dark web
British law enforcement comes a cropper in an incident which should - but probably won't - force a rethink of dreadful data storage policies.
Anthropic's rogue agents launch "real-world" attacks, join OpenAI's models in the wild
Bots gain access to the open internet in a grim omen of the grave security risks agentic AI poses to enterprises and digital civilisation itself.
Critical Systems
Cloudflare shows how a single failure can wipe an entire country off the internet
"These incidents underscore the fragility of internet infrastructure, but also the remarkable stability global systems maintain when operating normally."
Security
The questions security teams should be asking about China's "Mythos rival" TuLongFeng
Black Duck's Collin Hogue-Spears decodes the debate over whether China's new AI vulnerability finder rivals Anthropic's US-made bug hunter.
Systemic Risk
Financial systems are exposed to a structural AI risk with "no effective mitigation," EU warns
European Systemic Risk Board issues frightening forecast setting out the dangers of frontier artificial intelligence.
AI
"A productive equilibrium": How to scale agentic AI without losing control
"AI agents are emerging not as a replacement for human capability, but as powerful partners in amplifying it."
Security
Russian "Laundry Bear" threat actor rinses Western victims with zero-click exploit
Intelligence agencies get lathered up about a Moscow-linked espionage group also tracked as Void Blizzard.
Crime
The Home Office has a huge cybercrime blind spot in its police forecasting data
Computer crooks are more likely to be male - but that's about all we know about who will go to the digital dark side.
AI
Rogue OpenAI agents escape into the wild, attack Hugging Face and wreak havoc on GitHub
"We consider this incident to be an unprecedented security incident, involving state-of-the-art cyber capabilities."
Security
Hollowgraph malware turns Microsoft 365 calendars into secret-stealing "dead drop"
Command-and-control tool targets Israeli entities and shares technical similarities with a backdoor previously linked to an Iranian threat actor.
AI
"Nine seconds of terror": How to stop AI agents wiping out systems at machine speed
How can organisations protect themselves against bad bots hellbent on destroying core production data?
Financial Systems
Agentic AI demands an upgrade to financial system resilience, Bank of England warns
Central bank warns that "stronger defences are not enough" amid growing concerns about the weaponisation of autonomous security tools.
Crime
How cybercriminals are industrialising the trade in stolen healthcare data
Inside the underground criminal ecosystem where private information is bought and sold on a global scale.
Financial Systems
Stablecoins could become a systemic risk to global financial stability, central banks warn
Asset-backed digital currencies are set to enter widespread usage and pose