Toward Comprehensive Risk Assessments and Assurance of AI-Based Systems

Novel safety, socio-economic, and ethical harms arising from the deployment of AI-based systems have led to a breadth of work seeking to map, measure, and mitigate against newly found risks. These works have heavily leveraged techniques and terminology from the fields of System Safety Engineering...

Exploit for Deserialization of Untrusted Data in Facebook React

🎨 react2shellexploitvisualized - Visualize Vulnerabilities wit...

EUVD-2025-3973

Malicious code in bioql PyPI...

CVE-2025-24886

pwn.college is an education platform to learn about, and practice, core cybersecurity concepts in a hands-on fashion. Incorrect symlink checks on user specified dojos allows for users admin not required to perform an LFI from the CTFd container. When a user clones or updates repositories, a check...

CVE-2025-24886 pwn.college has Symlink LFI in Dojo repos

pwn.college is an education platform to learn about, and practice, core cybersecurity concepts in a hands-on fashion. Incorrect symlink checks on user specified dojos allows for users admin not required to perform an LFI from the CTFd container. When a user clones or updates repositories, a check...

Gamifying machine learning for stronger security and AI models

To stay ahead of adversaries, who show no restraint in adopting tools and techniques that can help them attain their goals, Microsoft continues to harness AI and machine learning to solve security challenges. One area we’ve been experimenting on is autonomous systems. In a simulated enterprise...

Gamifying machine learning for stronger security and AI models

To stay ahead of adversaries, who show no restraint in adopting tools and techniques that can help them attain their goals, Microsoft continues to harness AI and machine learning to solve security challenges. One area we’ve been experimenting on is autonomous systems. In a simulated enterprise...