noob6t5

noob6t5
41 posts
Deceptive AI Doesn’t Break the Rules. It Optimizes Around Them: with game theory
learning game theory part 0
Aug 24, 20263 min read
Game Theory for AI Security Part 1
Defender Strategies The defender chooses a security policy \(D \in \mathcal{D}\) where: $$\mathcal{D} = \{\text{baseline}, \text{hardened}, \text{monitoring}\}$$ Attacker Strategies The attacker choos
Aug 23, 20263 min read
Insecure Firestore Security Rules & PII Exposure
After poking with firebase R/W Realtime Database (Unauthenticated): https://[REDACTED].firebaseio.com/.json (Access Denied) Storage Bucket (Unauthenticated): https://firebasestorage.googleapis.com/v
Aug 22, 20263 min read
Payment Bypass Flaw in TechPSC HUB
Payment 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, 20262 min read
`ls` That Saved Me From Deleting Weeks of Work (AGAIN)
IMP Note: `ls -d regex`
Jun 27, 20261 min read
Pickle Deserialization RCE via Model Upload Endpoint
Link: https://www.ratctf.com/challenges/synapse-lab This challenge revolves around a classic but still heavily abused primitive: unsafe Python pickle deserialization exposed through a model upload API
Jun 11, 20264 min read
Beyond the Canvas: Exploiting an Unsanitized Side-Channel in draw.io
CVE-2026-46642 : Imagine opening a .drawio file and having your entire design silently exfiltrated to a remote server—all by a simple drag-and-drop.
May 12, 20263 min read
How OPT(ADD).Mathematics Builds the Foundation for AI/ML World
Based on the course and curriculum of NEB
Apr 14, 20267 min read
Deceptive AI Doesn’t Break the Rules. It Optimizes Around Them.
Finding while researching on AI Deception
Apr 12, 20263 min read