I'm a research assistant at CISPA and an undergraduate at BITS Goa. My work explores the intersection of ML, interpretability, security, and reverse-engineering — from understanding how LLMs reason and fail, to building more transparent and resilient AI systems.
I am actively looking for Research Engineer / Fellow positions in teams involving AI Security & Safety or LLM Reasoning. Moreover, I'm also interested in research collaborations and PhD opportunities with advisors exploring AI Security, Privacy or Distributed Systems.
📧 Please email me if you'd like to chat!
>publications & preprints
GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs
Advik Raj Basani, Xiao Zhang
Conference on Neural Information Processing Systems (NeurIPS) 2025
Diversity Boosts AI-Generated Text Detection
Advik Raj Basani, Pin-Yu Chen
DIGBUGS Workshop @ International Conference on Machine Learning (ICML) 2025
G-GQSA: Exploiting Feature-Based Vulnerabilities and Enhancing Adversarial Resilience in Android Malware Detection
Advik Raj Basani, Hemant Rathore
IEEE Consumer Communications & Networking Conference (CCNC) 2025
When Less is More: Achieving Faster Convergence in Distributed Edge Machine Learning
Advik Raj Basani, Siddharth Chaitra Vivek, Advaith Krishna, Arnab K. Paul
IEEE International Conference on High Performance Computing, Data, and Analytics (HiPC) 2024
>blogs
🚧 coming soon...
>photos
just a few pictures that I thought looked cool
