Introducing DVAIB - Damn Vulnerable AI Bank
DATE: 2025-12-27T20:44:00+04:00
SYSTEM: ai security
Can You Trick an AI Into Giving You Free Money? Introducing DVAIB - The World’s Most Vulnerable AI Bank
What if there was a bank where the AI assistant was… a little too helpful? A bank where smooth talking might just convince the AI to deposit a …
Multi-Turn Jailbreaks and “Psychological Manipulation” Attacks: Why Single-Turn Defenses Fail
DATE: 2025-12-23T23:47:00+04:00
SYSTEM: ai attacks
The AI doesn’t break on the first question. It breaks on the tenth.
The Conversation That Changed Everything Picture this: A researcher sits at their terminal, chatting with one of the world’s most advanced AI systems. The conversation starts …
Policy-as-Code for AI Workloads in Kubernetes: Kyverno/OPA Patterns for Model and Data Safety
DATE: 2025-12-23T21:26:17+04:00
SYSTEM: Agentic AI
1. Why This Matters Your container is signed. Your image is scanned. Your CVE count is zero.
None of that stops a backdoored model from running inference.
Container security and model security are different problems. Traditional Kubernetes hardening protects …
Securing Agentic AI: Roadmap Part-10
DATE: 2025-12-07T20:48:00+04:00
SYSTEM: Agentic AI
Part 10. Implementation Roadmap 10.0 Why you need a roadmap, not a random pile of bots You now have:
Agent patterns
Multi agent topologies
HITL designs
Threats and controls
Identity, architecture, governance
Securing Agentic AI: Governance Framework Part-9
DATE: 2025-12-07T14:59:00+04:00
SYSTEM: Agentic AI
Part 9. Governance Framework 9.0 Why you need actual governance, not “vibes” At small scale, you can ship an agent, watch it in Prod, and fix things as they break.