PPhying中文
Curated security research, vulnerabilities, advisories and tools for practitioners.

Junior devs ‘can’t actually code’, AI coding risks, security researchers decry inscrutable AI – OffSec roundup for CISOs

yeswehack.com | research | #ai-security | #red-teaming | #llm | #encryption | #ciso | #ai-coding | #icloud
📄 Raw .md⬇️ Download .md🔗 Original ↗

Summary

CISO roundup: junior devs' over-reliance on AI coding assistants sparks debate; researchers decry inscrutable AI; the UK iCloud encryption downgrade raises privacy fears; AI red-teaming lessons.
Published
Collected

Related coverage

blog · netspi.com
Ask These 5 AI Cybersecurity Questions for a More Secure Approach to Adversarial Machine Learning
NetSPI offers five questions security leaders should ask about AI/ML deployments, covering business use-case, model objectives, and training data, to counter adversarial machine learning risks.
research · blog.quarkslab.com
Android Data Encryption in depth
An in-depth study of Android data-at-rest encryption: how it works, which components attackers with high-end software vulnerabilities target, and PoCs against TrustZone Gatekeeper and Weaver.
research · blog.quarkslab.com
A glimpse of ext4 filesystem-level encryption
A peek at ext4 filesystem-level encryption in Linux 4.1: Google's per-directory scheme, the ext4-crypt userspace tool, and why the author calls the implementation unstable and not production-ready.
research · projectdiscovery.io
How abliterated models can get you pwned
# How abliterated models can get you pwned Oct 6, 2026 · Prince Chaddha Any open model whose weights have been edited can carry a backdoor, whether it's a task-specific fine-tune, a merged adapter...
research · vercel.com
Everything hackable will get hacked
Open-weight models that allow perform offensive research present an emerging cybersecurity challenge. But you do not need to wait for specialized models to begin defensive cybersecurity work.
research · vercel.com
DeepsecBench: evaluating model performance in finding cybersecurity vulnerabilities
Today we're releasing DeepsecBench, a benchmark that evaluates how well different models find security vulnerabilities in application code.
Back