Mukund Hirani
RAXE - AI Runtime Security
Dubai, United Arab Emirates
Actions
Mukund Hirani is the founder of RAXE, an AI Runtime security company building transparent, edge-first detection systems using embedding models. He began his career in cybersecurity and incident response, defending complex environments against nation-state threats across critical infrastructure and enterprise systems.
Mukund’s perspective bridges cybersecurity, applied machine learning, and product engineering, with a strong emphasis on systems that actually ship and hold up in production.
Links
Area of Expertise
Topics
300M Parameters vs the Agent: Why Security AI Should Run Locally
As AI agents gain access to tools, files, business systems and infrastructure, a common security pattern is emerging: use another large model to decide whether the first model's behaviour is safe.
We tried a different approach, placing a small, specialised security model close to the runtime boundary. That led to several uncomfortable engineering discoveries.
A static INT8 transformation left the model running while pushing benign false positives towards 90%. Keeping the embedding model's full 768-dimensional representation increased median inference latency by roughly 34% without improving primary threat detection. And a semantic-similarity signal that appeared highly confident turned out to flag 100% of both benign and malicious populations at its configured threshold.
This session explains the architecture that survived those failures: a narrow binary semantic decision, specialised classifier heads for context, deterministic rules where certainty exists, novelty signals for uncertainty, and larger-model adjudication only where a local model has demonstrably reached its limit.
The question is not whether small models can replace frontier models. It is which security decisions ever needed a frontier model in the first place.
Embeddings Meet Runtime Threat Detection: Explainable, Quantised, Multi-Head Security
In this talk, we argue that embedding models and threat detection are architectural cousins, and show how a transparent, dual-layer detection design combining explainable signature rules with lightweight, quantised classifiers can outperform brittle rules or opaque ML alone.
We’ll focus on three practical insights
+ why confidence scores often lie
+ how fp32→fp16→int8 quantization subtly breaks scoring assumptions
+ how a simple multi-head voting policy restores both robustness and explainability.
The talk closes with what didn’t work, and a minimal blueprint attendees can apply immediately.
Mukund Hirani
RAXE - AI Runtime Security
Dubai, United Arab Emirates
Links
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top