PinnedVSec·Aug 4, 2025Cryptographic Verification for ML Models with HashTraceAIThis is an experimental project exploring how cryptographic methods can be applied to machine learning model integrity. HashTraceAI is a…
VSec·Nov 7, 2025Can AI Defenses Trained on One Model Protect Another? Testing Cross-Architecture DefensiveTokensVincent Sheahan, NYU Cyber Fellow
VSec·Sep 15, 2025Solving Prompt Injection: A Breakthrough Defense for AI DevelopersLarge language models (LLMs) aren’t just chatbots anymore. They’re becoming the core of complex, real-world systems. But with more…
VSec·Aug 14, 2025IAM Permissions Sprawl: The Crisis We Created and How to Fix ItJust about every security team I’ve worked with has the same hidden embarrassment: a spreadsheet buried deep in some folder with a name…
VSec·Aug 10, 2025When “Local” Isn’t Local: The Critical AI Security Flaw You Probably MissedCVE-2025–49596 showed how insecure defaults and browser trust in localhost can lead to silent remote code execution. No malware. No…
VSec·Apr 21, 2023crAPI — Broken Object Level Authorization (BOLA)Broken Object Level Authorization (BOLA) vulnerabilities occur when an application fails to properly enforce access controls at the object…
VSec·Apr 20, 2023crAPI — Broken User AuthenticationBroken User Authentication is a common security vulnerability in which an API does not properly authenticate user requests or does not…