Available for opportunities
I build secure
intelligent systems.
K Harshit — CS undergrad at PES University specializing in LLM security, adversarial ML, and building production-grade AI threat detection pipelines.
Projects
Loading projects...
Technical Skills
Organized by domain — from core languages to specialized security and ML tooling.
Languages & Core
01Primary programming languages
PythonJavaCJavaScriptTypeScriptSQL
AI & Machine Learning
02ML frameworks, NLP, and model training
PyTorchHugging FaceNLPGANsReinforcement LearningSentenceTransformersCLIP / CLAPVector EmbeddingsXAI (SHAP)LangChain
Security & Adversarial
03Offensive/defensive security and LLM safety
LLM SecurityAdversarial MLThreat ModelingOWASP Top 10PentestingSteganographyJWT Auth
Backend & Data
04Server frameworks, databases, and APIs
Spring BootFastAPIFlaskNode.jsREST APIsMongoDBChromaDBFAISSNext.js
Systems & Networking
05Low-level systems and network programming
Socket ProgrammingLinuxBashDockerTUN/TAP InterfacesNmap
Tools & Workflow
06Development tools and platforms
Git / GitHubStreamlitNetworkX
Experience
Summer Research Intern
CCNCS, PES University
- Designed XJailGuard, a modular LLM security framework to detect multi-turn and cross-lingual prompt injection attacks in transformer-based models.
- Built multilingual classification pipelines using PyTorch and Hugging Face, incorporating sliding-window contextual memory for adversarial intent detection.
- Improved jailbreak detection accuracy from 8-12% baseline to 91-93% through layered input/output filtering and zero-trust validation.
- Integrated SHAP-based Explainable AI and evaluated performance using false positive/negative rates and latency benchmarks; authored for ICICC 2025 publication.
PyTorchHugging FaceSHAPNLP
Education
B.Tech in Computer Science and Engineering
PES University, Karnataka, India
8.54CGPA
On track
Achievements
Prof. C N R Rao Merit Scholarship
Awarded for academic excellence at PES University.
Certifications
Cybersecurity - Basics of Red Teaming
Fundamentals of ethical hacking, reconnaissance, exploitation, and post-exploitation techniques.