Nisarga Gondi

Pittsburgh, PA

ngondi@andrew.cmu.edu

I work where ML meets real products and real adversaries, on systems you can break and then make harder to break. (the adversaries are more punctual.) I’m a grad student at CMU INI (AIE-IS), working on applied ML and AI security at CyLab. Right now that’s Self-Evolving Defense (SED) for LLM agents (co-first-author paper under review at ACL ARR). Before CMU I shipped models at Samsung PRISM and built Ericsson’s Quick Dimensioning Tool, cutting profile selection from hours to minutes. I care about results you can measure.

Resume (PDF)

Stack. Python, PyTorch, LangGraph, Kotlin/Android, ONNX, Kubernetes, PostgreSQL. (yes, all of them. no, not at once.)

Undergrad and older project write-ups: Google Sites portfolio.

Publications

ARR
Self-Evolving Defense: Continual Security Policy Learning for LLM Agents

Minh Nhat Le, Nisarga Gondi, Yibo Peng, Ronghao Ni, Limin Jia, Beidi Chen, and Haizhong Zheng

2026

Under review, ACL Rolling Review

Abs arXiv Bib Code Website

LLM agents increasingly read untrusted content, call external tools, and modify software repositories, which exposes them to jailbreaks, prompt injection, and insecure code generation. We present Self-Evolving Defense (SED), a training-free framework that distills harmful agent trajectories into reusable security policies and retrieves the relevant ones for later tasks, so a frozen agent keeps adapting without any weight update.
@unpublished{gondi2026sed, title = {Self-Evolving Defense: Continual Security Policy Learning for LLM Agents}, author = {Le, Minh Nhat and Gondi, Nisarga and Peng, Yibo and Ni, Ronghao and Jia, Limin and Chen, Beidi and Zheng, Haizhong}, year = {2026}, note = {Under review, ACL Rolling Review}, }
IEEE
Multi-Constraint Time Series Imputation

Nisarga Gondi and Kayarvizhy N

In IEEE Pune Conference (INDIACom), 2024

Abs DOI Bib Code

A multi-constraint framework that sequences imputation algorithms across missingness, series length, and dimensionality, rather than trusting any single method to win everywhere.
@inproceedings{gondi2024imputation, title = {Multi-Constraint Time Series Imputation}, author = {Gondi, Nisarga and N, Kayarvizhy}, booktitle = {IEEE Pune Conference (INDIACom)}, year = {2024}, doi = {10.23919/INDIACom66777.2025.11115894}, }
IJAI
An Intelligent Plant Disease Detection using Twin Attention Optimal CNN

Nisarga Gondi, Prameetha, and others

IAES International Journal of Artificial Intelligence, 2026

Accepted

Abs Bib

A twin-attention CNN architecture for plant disease detection that focuses the model on diseased regions instead of background leaf texture.
@article{gondi2026plantdisease, title = {An Intelligent Plant Disease Detection using Twin Attention Optimal CNN}, author = {Gondi, Nisarga and Prameetha and others}, journal = {IAES International Journal of Artificial Intelligence}, year = {2026}, note = {Accepted}, }

Get in touch

Happy to talk research, AI security, or anything you're building.