Nilaksh Das · Georgia Institute of Technology

Nilaksh Das

Hi! I am Nilaksh, a PhD student at Georgia Institute of Technology in the School of Computational Science and Engineering, where I am advised by Dr. Duen Horng Chau.

My research focuses on Adversarial ML and interpretability of vulnerabilities in AI models. I am currently investigating strategies to secure AI models from causative and exploratory attacks.

I am also an active member of the Polo Club of Data Science where we conduct research spanning across data mining, machine learning, human-computer interaction and information visualization.

Publications

Mask The Bias: Improving Domain-Adaptive Generalization of CTC-based ASR with Internal Language Model Estimation
N. Das, M. Sunkara, S. Bodapati, J. Cai, D. Kulshreshtha, J. Farris, K. Kirchhoff
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023.
DOI PDF

SkeleVision: Towards Adversarial Resiliency of Person Tracking with Multi-Task Learning
N. Das, S. Peng, D. H. Chau
ECCV 2022 Workshop on Adversarial Robustness in the Real World (ECCV-AROW), 2022.
DOI PDF Code

Hear No Evil: Towards Adversarial Robustness of Automatic Speech Recognition via Multi-Task Learning
N. Das, D. H. Chau
Proceedings of the Annual Conference of the International Speech Communication Association (Interspeech), 2022.
DOI PDF

Listen, Know and Spell: Knowledge-Infused Subword Modeling for Improving ASR Performance of OOV Named Entities
N. Das, M. Sunkara, D. Bekal, D. H. Chau, S. Bodapati, K. Kirchhoff
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022.
Top 50 ICASSP22 posters
DOI PDF Project

A Cluster-then-label Approach for Few-shot Learning with Application to Automatic Image Data Labeling
R. Wu, N. Das, S. Chaba, S. Gandhi, D. H. Chau, X. Chu
ACM Journal of Data and Information Quality (JDIQ), 2022.
DOI

NeuroMapper: In-browser Visualizer for Neural Network Training
Z. Zhou, K. Li, H. Park, M. Dass, A. P. Wright, N. Das, D. H. Chau
IEEE Visualization Conference (IEEE VIS), 2022.
PDF Demo Code

DetectorDetective: Investigating the Effects of Adversarial Examples on Object Detectors
S. Vellaichamy, M. Hull, Z. J. Wang, N. Das, S. Peng, H. Park, D. H. Chau
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
DOI PDF Demo Video

NeuroCartography: Scalable Automatic Visual Summarization of Concepts in Deep Neural Networks
H. Park, N. Das, R. Duggal, A. P. Wright, O. Shaikh, F. Hohman, D. H. Chau
IEEE Transactions on Visualization and Computer Graphics (IEEE VIS), 2021.
Top 4 IEEE VIS21 papers
Invited to ACM SIGGRAPH 22
DOI PDF Demo

Best of Both Worlds: Robust Accented Speech Recognition with Adversarial Transfer Learning
N. Das, S. Bodapati, M. Sunkara, S. Srinivasan, D. H. Chau
Proceedings of the Annual Conference of the International Speech Communication Association (Interspeech), 2021.
DOI PDF Project Video

SkeletonVis: Interactive Visualization for Understanding Adversarial Attacks on Human Action Recognition Models
H. Park, Z. J. Wang, N. Das, A. S. Paul, P. Perumalla, Z. Zhou, D. H. Chau
Proceedings of the AAAI Conference on Artificial Intelligence, Demonstration Track (AAAI Demo), 2021.
DOI PDF Demo Video

EnergyVis: Interactively Tracking and Exploring Energy Consumption for ML Models
O. Shaikh, J. Saad-Falcon, A. P. Wright, N. Das, S. Freitas, O. Asensio, D. H. Chau
Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems (CHI), 2021.
DOI PDF Code Video

GOGGLES: Automatic Image Labeling with Affinity Coding
N. Das, S. Chaba, R. Wu, S. Gandhi, D. H. Chau, X. Chu
ACM International Conference on Management of Data (SIGMOD), 2020.
DOI PDF Code Tweet

Bluff: Interactively Deciphering Adversarial Attacks on Deep Neural Networks
N. Das*, H. Park*, Z. J. Wang, F. Hohman, R. Firstman, E. Rogers, D. H. Chau
IEEE Visualization Conference (IEEE VIS), 2020.
DOI PDF Demo Code

Massif: Interactive Interpretation of Adversarial Attacks on Deep Learning
N. Das*, H. Park*, Z. J. Wang, F. Hohman, R. Firstman, E. Rogers, D. H. Chau
Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems (CHI), 2020.
DOI PDF Code

CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization
Z. J. Wang, R. Turko, O. Shaikh, H. Park, N. Das, F. Hohman, M. Kahng, D. H. Chau
IEEE Transactions on Visualization and Computer Graphics (IEEE VIS), 2020.
Top of GitHub Trending list
Top 4 TVCG Papers
Invited to ACM SIGGRAPH 21
DOI PDF Demo Code Video

CNN 101: Interactive Visual Learning for Convolutional Neural Networks
Z. J. Wang, R. Turko, O. Shaikh, H. Park, N. Das, F. Hohman, M. Kahng, D. H. Chau
Extended Abstracts of ACM Conference on Human Factors in Computing Systems (CHI), 2020.
DOI PDF Code Video

MLsploit: A Framework for Interactive Experimentation with Adversarial Machine Learning Research
N. Das, S. Li, C. Jeon, J. Jung*, S. T. Chen*, C. Yagemann*, E. Downing*, H. Park, E. Yang, L. Chen,
M. E. Kounavis, R. Sahita, D. Durham, S. Buck, D. H. Chau, T. Kim, W. Lee
KDD Project Showcase, 2019.
Proceedings PDF

The Efficacy of SHIELD under Different Threat Models
C. Cornelius, N. Das, S. T. Chen, L. Chen, M. E. Kounavis, D. H. Chau
KDD Workshop - Learning and Mining for Cybersecurity (LEMINCS), 2019.
Proceedings PDF

Visual Analytics for Interpretability on Deep Neural Networks
H. Park, F. Hohman, N. Das, C. Robinson, D. H. Chau
NeurIPS Workshop - Women in Machine Learning (WiML), 2019.

MLsploit: A Cloud-Based Framework for Adversarial Machine Learning Research
N. Das, S. Li, C. Jeon, J. Jung*, S. T. Chen*, C. Yagemann*, E. Downing*, H. Park, E. Yang, L. Chen,
M. E. Kounavis, R. Sahita, D. Durham, S. Buck, D. H. Chau, T. Kim, W. Lee
Black Hat Asia - Arsenal, 2019.
Abstract Code Project Video

ADAGIO: Interactive Experimentation with Adversarial Attack and Defense for Audio
N. Das, M. Shanbhogue, S. T. Chen, L. Chen, M. E. Kounavis, D. H. Chau
European Conference on Machine Learning & Principles & Practice of Knowledge Discovery in Databases (ECML-PKDD), 2018.
DOI PDF Code Video

SHIELD: Fast, Practical Defense and Vaccination for Deep Learning Using JPEG Compression
N. Das, M. Shanbhogue, S. T. Chen, F. Hohman, S. Li, L. Chen, M. E. Kounavis, D. H. Chau
ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD), 2018.
Audience Appreciation Award (runner-up)
DOI PDF Code Project Article Video Tweet

Compression to the Rescue: Defending from Adversarial Attacks Across Modalities
N. Das, M. Shanbhogue, S. T. Chen, F. Hohman, S. Li, L. Chen, M. E. Kounavis, D. H. Chau
KDD Project Showcase, 2018.
Proceedings PDF

Defense against Adversarial Attacks using JPEG Compression
N. Das, M. Shanbhogue, S. T. Chen, F. Hohman, L. Chen, M. E. Kounavis, D. H. Chau
NIPS Workshop - Women in Machine Learning (WiML), 2017.

Training a Generative Agent Grounded in Cooperative Visual Dialog with Deep Reinforcement Learning
A. Kalia, N. Das, M. Shanbhogue, V. Parthasarathy
NIPS Workshop - Women in Machine Learning (WiML), 2017.

Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compression
N. Das, M. Shanbhogue, S. T. Chen, F. Hohman, L. Chen, M. E. Kounavis, D. H. Chau
arXiv preprint arXiv:1705.02900, 2017.
PDF Article

PASSAGE: A Travel Safety Assistant with Safe Path Recommendations for Pedestrians
M. Garvey, N. Das, J. Su, M. Natraj, B. Verma
ACM International Conference on Intelligent User Interfaces (IUI), 2016.
DOI