Attention: You are using an outdated browser, device or you do not have the latest version of JavaScript downloaded and so this website may not work as expected. Please download the latest software or switch device to avoid further issues.
| 12 Mar 2026 | |
| Written by Gabi Gerber | |
| Attacks & Threats |
| Security Operation Center, Hacking Topics |
The picoCTF 2026 competition from Carnegie Mellon University is currently underway (10 days), and you can still register:
I got a tip from one of the participants in case you haven't heard of it and need some more practice 😉. It seems to be very taff.
picoCTF is the largest cybersecurity hacking competition for middle school, high school, and college students. Participants aged 13 and older of all skill levels are encouraged to compete. Competitors must reverse-engineer, break, hack, decrypt, and think creatively and critically to solve the challenges and capture the digital flags.
Dark Reading Confidential Episode 20: Expert Rich Mogull reflects on lessons cyber teams should pull from the OpenAI agent's attack on Hugging Face. More...
New research shows how attackers can use security alerts and blocked events to manipulate and hijack AI agents. More...
A study of more than 6,000 patches found that even working patches can introduce new bugs, break something else, or are … More...
Advanced LLMs escaped their sandboxes while attempting to achieve a non-malicious benchmark test objective. More...
A myriad of software makes up the typical AI harness, and trust issues between the components can create concerning atta… More...
Dark Reading Confidential Episode 20: Expert Rich Mogull reflects on lessons cyber teams should pull from the OpenAI agent's attack on Hugging Face. More...
New research shows how attackers can use security alerts and blocked events to manipulate and hijack AI agents. More...
A study of more than 6,000 patches found that even working patches can introduce new bugs, break something else, or are … More...
Advanced LLMs escaped their sandboxes while attempting to achieve a non-malicious benchmark test objective. More...
A myriad of software makes up the typical AI harness, and trust issues between the components can create concerning atta… More...
