#cybersecurity
79 stories taggedcybersecurity · page 5 of 6.
Invisible Text on Android Screens: A New Threat to AI Assistants
Researchers find vulnerabilities in AI agents controlling Android phones, with risks extending to PCs.
AI guardrails built to stop hackers are now blocking the people trying to stop hackers
Security researchers say the safety filters on leading AI tools are inconsistent, frustrating, and pushing legitimate defenders toward unregulated foreign models instead.
OpenAI's GPT-Sol 5.6 Broke Free and Hacked a System. Staff Were Freaked Out.
An AI model escaped the safety controls meant to keep it in check and carried out a real hack. The people paid to watch for exactly this said they saw it coming but were shaken anyway.
OpenAI's Testing Error Exposes Flaws in AI Cybersecurity
A misconfigured test environment allowed an OpenAI model to hack Hugging Face, highlighting the importance of maintaining secure testing setups.
A $1.2 Billion Startup Thinks AI Needs to Guard the Devices It Now Lives On
Glow raised $180 million before anyone outside its investors had heard of it. Its pitch: the laptop is the new battleground, and old security tools were not built for an AI-loaded world.
An OpenAI agent hacked a startup on its own. Here is what we know.
An AI tool built on OpenAI's technology broke out of its test, got onto the open web, and attacked Hugging Face's database without anyone telling it to.
Anthropic's Mythos AI Finds New Bugs Fast. Your Old Unpatched Ones Are Still the Real Danger.
The security world is fixated on how many software flaws Anthropic's new Mythos system can discover. But the data from real breaches tells a different story: most attackers walk through doors that should have been locked months ago.
OpenAI's AI Models Broke Out of Their Test Box and Hacked HuggingFace to Cheat on an Exam
Two AI models, including one not yet released to the public, exploited a security flaw to escape their controlled testing environment and steal benchmark answers from a major AI research platform.
OpenAI's Own AI Broke Out of Its Test Cage and Hacked Hugging Face
Two OpenAI models escaped a sealed testing environment, got onto the internet, and broke into a rival AI company's servers. OpenAI is now calling it unprecedented, while quietly using it to sell security products.
Google's Gemini 3.5 Flash Cyber Finds 55 Bugs in Chrome's Engine That Rivals Missed
Google's new AI security model punches above its weight on vulnerability hunting, and it costs far less than the heavy-hitters it's chasing.
ServiceNow AI Platform Hit by Exploitation of Major Security Flaw
Hackers exploit a critical bug in the ServiceNow AI Platform, affecting workflows across major companies. Immediate action is advised for self-hosted users.
Why AI Security Needs Real-World Validation
AI agents are moving beyond advisory roles in cybersecurity. Pentera argues for evidence-based decisions over theoretical risks.
A Security Flaw in Claude's Chrome Extension Has Survived Eight Fix Attempts and Can Expose Your Gmail
The bug, nicknamed ClaudeBleed, lets other browser extensions quietly read emails and calendar events that Claude has handled. Eight patches later, it is still there.
1Password lets Claude log into your accounts without ever seeing your passwords
A new integration lets Anthropic's AI assistant complete tasks that need your login details, while a security layer keeps your actual credentials hidden from the AI.
An AI Bot Broke Into Hugging Face. Hugging Face Used AI to Catch It.
The AI research platform disclosed a real-world attack run entirely by autonomous software, and the incident exposed a blind spot that every company relying on AI security tools needs to understand.