Portrait of Kishan N.

AI Security Researcher · Engineer · Builder

Kishan N.

I build defensive security tooling and study how neural networks represent what they know - treating both as the same problem: understanding complex systems well enough to trust them. Featured in Marimo Newsletter #26 for training Chitti on MoLab GPUs.

Years building
0
Years building
Certifications
0
Certifications
GitHub Projects
0
GitHub Projects

About

The story behind the work.

Kishan N.

It started with curiosity - the kind that asks “how does this actually work?” and isn’t satisfied until every layer has been peeled back.

That curiosity led from writing first programs to understanding networks, from breaking things ethically to building systems that protect them. Cybersecurity taught the importance of defense in depth.

AI opened a new frontier: not just building intelligent systems, but understanding how they represent and process information. Representation engineering - finding and modifying behavioral directions in activation space - is where those two paths converge.

Currently a CS student at Srinivas University, Mangalore, India - building toward AI security research and engineering opportunities globally.

Focus Areas

  • AI Safety & Alignment
  • Mechanistic Interpretability
  • Representation Engineering
  • Cybersecurity & Threat Detection

Technical Stack

  • Python, PyTorch, Transformers
  • PEFT, LoRA, Unsloth, TRL
  • Linux, Docker, CUDA
  • JavaScript, React, Node.js

Research Interests

  • Behavioral direction extraction in LLMs
  • Abliteration & controlled steering
  • AI security tooling & red-teaming
  • Blue team automation & SOC engineering
The Journey

Every chapter built the next.

From first lines of code to the frontiers of AI research - chapter by chapter.

Projects

Each one treated as its own product - a problem, a solution, and what it taught me.

Chitti - AI coding assistant built on MoLab GPUs
Flagship · Featured in Marimo Newsletter #26

Chitti

A 7B coding assistant fine-tuned for security research - built on Qwen2.5-Coder-7B-Instruct using abliteration + LoRA on MoLab's NVIDIA RTX PRO 6000 GPUs. Hits 76.83% on HumanEval+, outperforming DeepSeek-Coder-7B. Full pipeline: dataset curation, fine-tuning, benchmarking, chat interface - all in marimo notebooks.

PyTorchTransformersLoRA / PEFTUnslothMoLab GPUsMarimo
Read the case study →
BugHunter - automated bug hunting framework

BugHunter

Automated bug hunting framework for security researchers - combines reconnaissance, enumeration, and vulnerability discovery into a unified workflow for efficient security assessments.

PythonReconEnumerationAutomation
View on GitHub →
Aegis Sentinel - real-time threat detection SOC platform

Aegis Sentinel

Real-time threat detection and SOC platform - multi-signal ML scoring, JWT auth, auto IP blocking, behavioral analysis. Rule-based + ML engine with 8 weighted features and a live Chart.js dashboard.

PythonFastAPIML ScoringJWTSQLite
View on GitHub →
PACS Security Auditor - healthcare DICOM security

PACS Security Auditor

Full-stack DICOM/PACS security auditing platform - exploitation simulation, HIPAA compliance mapping (45 CFR § 164.312), real-time web dashboard. Tested on DCM4CHEE + Orthanc Docker lab.

PythonFastAPIpynetdicomHIPAADocker
View on GitHub →
ShieldNet - AI-powered network IDS

ShieldNet

AI-powered network IDS using ML + Deep Learning (ANN, CNN, LSTM) to detect DoS, DDoS, PortScan, and Brute Force attacks on the CIC-IDS2017 dataset. Flask web interface for real-time prediction.

PythonTensorFlowFlaskLSTM/CNNSMOTE
View on GitHub →
FTP Honeypot - MITRE ATT&CK mapped SOC platform

FTP Honeypot

SOC-grade deception platform - multi-threaded FTP server emulation with automatic MITRE ATT&CK mapping, threat scoring, session replay, and SIEM-ready exports. Built for blue team training and threat intelligence.

PythonMITRE ATT&CKSOCRich TUI
View on GitHub →
Cyber Threat Intelligence Dashboard - live IOC lookup

CyberThreat Intelligence

Dockerized CTI platform - IOC lookup via VirusTotal + AbuseIPDB simultaneously, MongoDB persistence, Bootstrap dark dashboard. Full Docker Compose stack, app factory pattern, live threat analysis.

PythonFlaskMongoDBDockerVirusTotal API
View on GitHub →
HashForge - cryptographic hashing toolkit

HashForge

Cryptographic hashing toolkit with support for multiple algorithms, hash cracking utilities, and integrity verification tools for forensics and security research workflows.

PythonCryptographyForensicsHash Analysis
View on GitHub →
Web Vulnerability Scanner - OWASP Top 10 detection

Web Vulnerability Scanner

Automated scanner for detecting OWASP Top 10 and common web application vulnerabilities - built for security researchers and bug bounty hunting workflows.

PythonOWASPBug BountyAutomation
View on GitHub →
Flagship Project · Featured in Marimo Newsletter #26

Chitti

Chitti is a 7B coding assistant fine-tuned for security researchers and professional developers - built from scratch on MoLab's NVIDIA RTX PRO 6000 Blackwell GPUs using abliteration and LoRA fine-tuning, entirely in marimo notebooks. It outperforms DeepSeek-Coder-7B on HumanEval+ and was featured in the official Marimo Newsletter.

Problem

Security researchers need coding assistants that engage with security-adjacent requests - vulnerability analysis, exploit understanding, defensive tooling - without reflexive refusals that treat every security topic as off-limits.

Solution

Fine-tuned Qwen2.5-Coder-7B-Instruct using a two-stage pipeline: abliteration (Representation Engineering at alpha=2.0 across all 28 layers) to remove the refusal direction, followed by LoRA fine-tuning on OpenCodeInstruct to restore and improve coding capability.

Architecture

Based on Qwen2.5-Coder-7B-Instruct. Training pipeline: dataset curation → abliteration → LoRA fine-tuning → model merging → benchmark evaluation. All stages built and run in marimo notebooks on MoLab's GPU infrastructure.

Benchmark Results

HumanEval+ - 76.83%

Beats DeepSeek-Coder-7B (73%) and competitive with models 2× larger

MultiPL-E - 67.49%

Above Qwen2.5-Coder-7B baseline (65%) - multilingual code generation improved

LiveCodeBench - 23.5%

Competitive on real-world, competition-style coding problems

Training Pipeline

Phase 1 - Dataset Curation

OpenCodeInstruct selection and filtering in marimo notebooks

Phase 2 - Abliteration

Representation Engineering: refusal direction projected out of all 28 layers at alpha=2.0

Phase 3 - LoRA Fine-tuning

PEFT / Unsloth LoRA training on MoLab's RTX PRO 6000 Blackwell GPUs

Phase 4 - Benchmark Evaluation

HumanEval+, MultiPL-E, LiveCodeBench across 10+ programming languages

Current - Research & Platform Integration

REST API, enhanced inference pipeline, ongoing interpretability research

Recognition & Links

Research

Working at the intersection of AI interpretability, security, and safety.

Active Work

Active
Representation Engineering in LLMs

Implementation and extension of Turner et al. (2023) - extracting behavioral directions from activation space, studying the alpha parameter's effect on capability-behavior tradeoffs, and discovering framing sensitivity as a novel finding. Interactive marimo notebook on MoLab.

📓 MoLab Notebook arXiv:2310.01405
Active
Security for Agentic AI

Investigating the attack surface of AI agents - agent sandboxing, secure tool calling, prompt injection firewalls, AI identity and access control, and agent permission models. As AI systems become more capable and autonomous, the offensive security mindset becomes directly applicable to understanding and hardening agent infrastructure.

Exploratory
AI Memory and Persistent State

Exploring how AI agents can maintain persistent, structured memory across sessions - episodic, semantic, and procedural memory layers, knowledge graph integration, time-aware retrieval, and forgetting engines. Current systems treat memory as a vector database; the interesting research question is whether memory can evolve meaningfully over time without retraining.

Exploratory
Multi-Agent Governance and Lifecycle

Studying how multi-agent systems should be supervised, audited, and managed - conflict resolution between agents, permission hierarchies, agent lifecycle (birth, learning, evolution, retirement, knowledge transfer), and what an "operating system" for AI agents would actually look like at a systems level.

Ongoing
Blue Team Engineering and Threat Intelligence

Building SOC-grade defensive tools grounded in MITRE ATT&CK - honeypots, threat scoring, and detection engineering. Bridging offensive security knowledge into actionable defensive systems.

Publications, Recognition & Community Work

Press
Marimo Newsletter #26 - Training Coding Agents Spotlight

Featured by the Marimo team for training Chitti entirely on MoLab's NVIDIA RTX PRO 6000 Blackwell GPUs - dataset curation, fine-tuning, benchmarking, and chat interface, all in marimo notebooks.

Blog
Guest Blog - marimo.io

Technical writeup on the complete Chitti training pipeline - published on the official Marimo blog as a guest post, covering abliteration, LoRA fine-tuning, and benchmark evaluation methodology.

Notebook
Representation Engineering - Interactive MoLab Notebook

Submitted to MoLab Notebook Competition #2. Implements Turner et al. (2023) with toy NumPy examples, 2D activation space visualization, interactive alpha explorer, live before/after model comparison, and novel framing sensitivity findings documented as lessons learned.

Writeups
Hands-on Security Writeups

Documented CTF solutions, penetration testing exercises, and vulnerability research. Practical offensive security knowledge that grounds the defensive tooling work.

Community
Zorvyn Internship Scam - Exposed

Public documentation and technical investigation of a fraudulent internship scheme targeting CS students. Analysed the scam infrastructure, social engineering tactics, and published findings to protect the wider student community. An example of applied OSINT and community-first security research.

Certificates

Professional certifications with images - organized by discipline. Click any certificate to view.

Get in touch

Let’s build something.

Open to conversations on AI security research, interpretability, agentic systems, or security engineering. Whether you're building something ambitious, exploring a research idea, or just want to talk about what's next in AI and cybersecurity - reach out.