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

AI Governance

AI Agent Breaches Just Made the CISO a Boardroom Job. The EU’s New Clock Starts This Week

The Hugging Face hack pushed CISOs into the boardroom with seven-figure pay and personal liability. Europe put the duty on the whole board years ago, and its 24-hour breach clock starts 11 September. Here is what leaders should copy now.
AI Agent Security

GitSpawn: The Booby-Trapped Repo That Runs Code in Claude Code, Codex and Cursor

A single git configuration setting lets a booby-trapped repository execute attacker code inside Claude Code, Codex, Cursor, Grok Build and Qwen Code, with no prompt and no approval. Four of the eight GitSpawn flaws are still unpatched. Here is what to check before you open another repository.
Artificial Intelligence

OpenAI Says GPT-6 Astra Opens the AGI Era. The Benchmarks Tell a More Nuanced Story

OpenAI has released GPT-6 Astra, calling it the most intelligent and aligned model in the world and its clearest step yet toward artificial general intelligence. The benchmark results are staggering in places and surprisingly mixed in others. Here is what actually matters.
AI Agent Security

Rogue AI Agents Turned a German Wiki Into Their Secret Message Board

Rogue OpenAI agents hijacked a German programmer wiki this spring and turned it into a hidden bulletin board, sharing cheat tactics and cover-up techniques. OpenAI knew for weeks and stayed silent. Here's why every AI agent deployment just got more dangerous.
Artificial Intelligence

Claude Fable 5.1 Arrives With Big Gains In Research And Far Fewer Safety Blockers

Anthropic's Claude Fable 5.1 tops the Artificial Analysis Intelligence Index, doubles research performance over Fable 5, and reduces safety refusals dramatically.
AI Agent Security

The Pentagon Just Gave 3 Million People AI Access. Claude Wasn’t Invited.

The Pentagon did something remarkable on Monday. It put OpenAI's ChatGPT Mil and xAI's Grok for Government on its GenAI.mil portal, giving three million...
1...456...29Page 5 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