Deceptive AI Doesn’t Break the Rules. It Optimizes Around Them: with game theoryEveryone assumes deception in AI will look obvious — a system glitch, a sudden compute spike, or a glaring anomaly. That assumption is fundamentally wrong. The most effective deception doesn’t violateAug 24 · 3 min readnoob6t5.hashnode.dev
Game Theory for AI Security Part 1Defender Strategies The defender chooses a security policy \(D \in \mathcal{D}\) where: $$\mathcal{D} = \{\text{baseline}, \text{hardened}, \text{monitoring}\}$$ Attacker Strategies The attacker choosAug 23 · 3 min readnoob6t5.hashnode.dev
Insecure Firestore Security Rules & PII ExposureAfter poking with firebase R/W Realtime Database (Unauthenticated): https://[REDACTED].firebaseio.com/.json (Access Denied) Storage Bucket (Unauthenticated): https://firebasestorage.googleapis.com/v1Aug 22 · 3 min readnoob6t5.hashnode.dev
Payment Bypass Flaw in TechPSC HUBPayment bypass leads to full feature unlock ,bypass Link: https://techpsc.com/halloffame How This app work\s : sets 1 through 3 open freely, but selecting set 4 triggers a subscription payment prompt.Aug 16 · 2 min readnoob6t5.hashnode.dev
`ls` That Saved Me From Deleting Weeks of Work (AGAIN)I almost deleted 3 weeks of work coz I got a little too confident with a shell wildcard.I was cleaning up my recon workspace and wanted to remove a bunch of generated directories. rm -rf {reports,logsJun 27 · 1 min readnoob6t5.hashnode.dev