I am currently a sophomore in Department of Mathematics at MIT Manipal, majoring in Mathematics and Computing. I am working as a student researcher with Mars Rover Manipal (MRM) AI Research.
I’ve previously worked on adversarial attacks, which led to my interest in trustworthy machine learning. I’m especially curious about how robustness and reliability connect to AI safety. I’m still new to the AI safety space, but I’m actively learning and building a solid foundation in the area.
Bhagyesh Kumar*, A S Aravinthakshan*, Akshat Satyanarayan*, Ishaan Gakhar, Ujjwal Verma
AAAI 2026 Workshop on AI for Cyber Security
Student Researcher working on Adversarial Robustness and Mechanistic Interpretability.
Worked on ShareLM project under PhD candidate Shachar Don-Yehiya (Hebrew University).
Growth
Campus Leader
A representation-engineering framework that probes and intervenes on internal harmfulness and refusal signals in LLMs to calibrate safety behavior
View Code →Benchmarking SLMs on quantization and RLHF effects to measure bias and fairness across standard evaluation datasets.
View Code →Simulation of LLM agent collusion under Cournot competition strategies.
View Code →