Hey! alxk is a security and platform engineer with a decade in the field. He built the original cybersecurity safety evaluations framework at Google DeepMind, where he also threat modelled AI deployments and worked on adversarial testing of image and text watermarking for generative models. He previously led the platform and security team at TrueLayer.
❏ Papers.
⚐ Talks.
♨ Tools and projects.
❏ Papers.
⚐ Talks.
♨ Tools and projects.
✍ Posts.
-
Captioning images for retrieval: frontier vs 8B
-
GitOops! Attacking and defending CI/CD pipelines
-
AWS Org Logging: Centralization
-
Terraform Plan RCE
-
Security advantages of pull-based CD pipelines
-
kubelet: anonymous to cluster-admin
-
Revisiting Email Spoofing
-
Security-focused CI/CD Pipeline
-
Minikube RCE & VM Escape
-
DNS Rebinding Headless Browsers