Scholar
Krishna Kanth Nakka
Google Scholar ID: g_21RKoAAAAJ
EPFL
Citations & Impact
Citations
487
H-index
9
i10-index
9
Publications
20
Co-authors
18
list available
Publications
Resume (English only)
Academic Achievements
- Published several papers, including:
- - PII Jailbreaking in LLMs via Activation Steering Reveals Personal Information Leakage
- - Mammo-SAE: Interpreting Breast Cancer Concept Learning with Sparse Autoencoders
- - PrivacyScalpel: Enhancing LLM Privacy via Interpretable Feature Intervention with Sparse Autoencoders
- - NAT: Learning to Attack Neurons for Enhanced Adversarial Transferability
Research Experience
- Worked as a postdoctoral scientist at the Visual Intelligence for Transportation Lab (VITA) at EPFL under the supervision of Prof. Alexandre Alahi for eight months, until April 2023. Before joining EPFL, spent two years at Samsung Research Bangalore working on mobile camera algorithms. During undergraduate years, interned at the University of Alberta, the University of Queensland, and Philips Research.
Education
- PhD in Computer Science from EPFL in August 2022, supervised by Dr. Mathieu Salzmann and Prof. Pascal Fua. Graduated from the Department of Electrical Engineering at IIT Kharagpur in 2015 with a dual degree (Master’s and Bachelor’s).
Background
- Currently working in the Privacy Team at the Trustworthy Technology Lab, Huawei Munich Research Center, focusing on the privacy and safety of large language models (LLMs). Research interests include studying privacy leakage in LLMs, unlearning of sensitive information, text anonymization, and understanding LLMs through mechanistic interpretability.
Miscellany
- Email / CV / Google Scholar / Github / LinkedIn / Thesis / Thesis Slides
