sailik image

Style-transferring one of Satyajit Ray's Feluda book-covers onto his portrait taken at the Golden Gate Bridge.


Curriculum Vitae


Once upon a time, Sailik was born in the city of Kolkata. Over the years, he has developed a taste for life-long learning, thinking, coding, reading, clicking pictures, eating lots of food and listening to a wide variety of music.

After completing his Ph.D. at Arizona State University with Dr. Subbarao Kambhampati, he joined Amazon AI's Lex team as an Applied Research Scientist. He is interested in identifying failure points of cyber systems and deep learning models and proposing solutions can make these systems behave is a robust and reliable manner. In 2018, he was awarded the prestigious IBM Ph.D. Fellowship for his work.

Feel free to reach out to him with queries relating to his work (or just say a 'hi'). You can download a copy of his CV here.

He likes to talk (a lot) and spends a lot of time doing so, oftentimes, on random topics completely unrelated to his research interests. He is self-critical about his shortcomings and feels correcting them will help him become a better person.

The pronunciation of his name in his native language, Bengali, is Sho-e-lik. It means the aesthetic quality of any work.


sailik image

Ph.D. (2015-2020) in Computer Science
Arizona State University

Jadavpur University logo

B.E. (2009-2013) in Computer Science & Engineering
Jadavpur University

St. Xavier's collegiate school logo

Alumnus (1997-2009)
St. Xavier's Collegiate School



📅 2021

On the Robustness of Intent Classification and Slot Labeling in Goal Oriented Dialogue Systems to Real-world Noise

Sailik Sengupta*, Jason P Krone*, Saab Mansour

NLP for Conversational AI, EMNLP'21 (Also presented at ICLR'21 Workshop on Robust Machine Learning)

Software Deception Steering through Version Emulation

Frederico Araujo, Sailik Sengupta, Jiyong Jang, Adam Doupé, Kevin Hamlen, Subbarao Kambhampati

HICSS, 2021

Imperfect ImaGANation: Implications of GANs Exacerbating Biases on Facial Data

Niharika Jain, Alberto Olmo, Sailik Sengupta, Lydia Manikonda, Subbarao Kambhampati

ICLR'21 Workshop on Synthetic Data Generation- Quality, Privacy, and Bias

Game-theoretic Model of Trust to Infer Human's Observation Strategy of Robot Behavior

Sailik Sengupta*, Zahra Zahedi*, Subbarao Kambhampati

RSS'21 Workshop on Robotics for People: Perspectives on Interaction, Learning, and Safety

📅 2020

The What, When, and How of Strategic Movement in Adversarial Settings:
A Syncretic View of AI and Security

Sailik Sengupta

Ph.D. Thesis

Multi-agent Reinforcement Learning in Bayesian Stackelberg Markov Games for Adaptive Moving Target Defense

Sailik Sengupta, Subbarao Kambhampati

NeurIPS Workshop on Real-World Reinforcement Learning (RWRL), 2020

'Why not give this work to them?' Explaining AI-Moderated Task-Allocation Outcomes using Negotiation Trees

Zahra Zahedi*, Sailik Sengupta*, Subbarao Kambhampati

NeurIPS Workshop on Co-operative Aritificial Intelligence (Co-op AI), 2020

Not all Failure Modes are Created Equal: Training Deep Neural Networks for Explicable (Mis)Classification

Alberto Olmo*, Sailik Sengupta*, Subbarao Kambhampati

ICML Workshop(s) on Uncertainty and Robustness in Deep Learning (UDL) and Human-In-the-Loop Learning (HILL), 2020

Moving Target Defense for Robust Fingerprinting of Electric Grid Transformers in Adversarial Environments

Sailik Sengupta, Kaustav Basu, Arunabha Sen, Subbarao Kambhampati

GameSec, 2020

A Survey of Moving Target Defenses for Network Security

Sailik Sengupta*, Ankur Chowdhary*, Abdulhakim Sabur, Dijiang Huang, Adel Alshamrani, Subbarao Kambhampati

IEEE Communications Surveys and Tutorials, 2020

RADAR: Automated Task Planning for Proactive Decision Support

Sachin Grover, Sailik Sengupta, Tathagata Chakraborti, Subbarao Kambhampati

HCI Journal on Unifying Human Computer Interaction and Artificial Intelligence, 2020 (Also presented at ICAPS, 2020 Journal Track)

RADAR-X: An Interactive Interface Pairing Contrastive Explanations with Revised Plan Suggestions

Karthik Valmeekam, Sarath Sreedharan, Sailik Sengupta, Subbarao Kambhampati

ICAPS Workshop on Explainable AI Planning (XAIP), 2020

DAPT 2020 - Constructing a Benchmark Dataset for Advanced Persistent Threats

Sowmya Myneni*, Ankur Chowdhary*, Abdulhakim Sabur, Sailik Sengupta, Garima Agrawal, Dijiang Huang, Myong Kang

ML-Hat, 2020 (co-located with KDD-2020)

📅 2019

General Sum Markov Games for Strategic Detection of Advanced Persistent Threats using Moving Target Defense in Cloud Networks

Sailik Sengupta, Ankur Chowdhary, Dijiang Huang, Subbarao Kambhampati

GameSec, 2019

MTDeep: Moving Target Defense to Boost the Security of Deep Neural Nets Against Adversarial Attacks

Sailik Sengupta, Tathagata Chakraborti, Subbarao Kambhampati

GameSec, 2019 (A preliminary version was presented at a AAAI-18 Workshop on Enginnering Secure and Dependable ML Systems)

Natural Language Generation with Keyword Constraints-- A Hybrid Approach using Supervised and Reinforcement Learning

Sailik Sengupta, He He, Batool Haider, Spandana Gella, Mona Diab

WeCNLP, 2019

Markov Game Modeling of Moving Target Defense for Strategic Detection of Threats in Cloud Networks

Ankur Chowdhary*, Sailik Sengupta*, Dijiang Huang, Subbarao Kambhampati

AAAI'19 Workshop on Artificial Intelligence for Cyber Security (AICS) (Preliminary version accepted to ICNC, 2019)

To Monitor or to Trust: Observing Robot's Behavior based on a Game-Theoretic Model of Trust

Sailik Sengupta*, Zahra Zahedi*, Subbarao Kambhampati

21st International Workshop on Trust in Agent Societies (co-located with AAMAS, 2019)

iPass: A Case Study of the Effectiveness of Automated Planning for Decision Support

Sachin Grover, Sailik Sengupta, Tathagata Chakraborti, Aditya Prasad Mishra, Subbarao Kambhampati

Naturalistic Decision Making, 2019

CAP: A Decision Support System for Crew Scheduling using Automated Planning

Aditya Prasad Mishra, Sailik Sengupta, Sarath Sreedharan, Tathagata Chakraborti, Subbarao Kambhampati

Naturalistic Decision Making, 2019

📅 2018

Moving Target Defense for the Placement of Intrusion Detection Systems in the Cloud

Sailik Sengupta, Ankur Chowdhary, Dijiang Huang, Subbarao Kambhampati

GameSec, 2018

MTDeep - Boosting the Security of Deep Neural Nets Against Adversarial Attacks with Moving Target Defense

Sailik Sengupta, Tathagata Chakraborti, Subbarao Kambhampati

AAAI'18 Workshop on Engineering Dependable and Secure Machine Learning Systems

An Investigation of Bounded Misclassification for Operational Security of Deep Neural Networks

Sailik Sengupta, Andrew Dudley, Tathagata Chakraborti, Subbarao Kambhampati

AAAI'18 Workshop on Engineering Dependable and Secure Machine Learning Systems

MA-RADAR - A Mixed-Reality Interface for Collaborative Decision Making

Tathagata Chakraborti*, Sailik Sengupta*, Subbarao Kambhampati

ICAPS, 2018 System Demo (Also to be presented at the UISP Workshop @ ICAPS, 2018)

Decomposable Intents in Goal-Directed Conversations: Dataset and Challenges for End-to-End Learning

Sailik Sengupta, Rashmi Gangadharaiah, Ajay Mishra, Mona Diab

WeCNLP Summit, 2018 (Retracted)

📅 2017

RADAR - A Proactive Decision Support System for Human-in-the-Loop Planning

Sailik Sengupta, Tathagata Chakraborti, Sarath Sreedharan, Satya Gautam Vadlamudi, Subbarao Kambhampati

AAAI Fall Symposium on Human-Agent Groups, 2017

ICAPS, 2017 System Demo (Was also presented at the UISP Workshop @ ICAPS, 2017)

A Game Theoretic Approach to Strategy Generation for Moving Target Defense in Web Applications

Sailik Sengupta, Satya Gautam Vadlamudi, Subbarao Kambhampati, Adam Doupé, Ziming Zhao, Marthony Taguinod, Gail-Joon Ahn

AAMAS, 2017 (Also presented at ADVERSE workshop @ AAMAS, 2017)

Moving Target Defense: A Symbiotic Framework for AI & Security

Sailik Sengupta

AAMAS (DC), 2017

📅 2016

Compliant Conditions for Polynomial Time Approximation of Operator Counts

Tathagata Chakraborti, Sarath Sreedharan, Sailik Sengupta, T. K. Satish Kumar and Subbarao Kambhampati

SoCS, 2016

Moving Target Defense For Web Applications Using Bayesian Stackelberg Games

Satya Gautam Vadlamudi, Sailik Sengupta, Subbarao Kambhampati, Marthony Taguinod, Ziming Zhao, Adam Doupé, Gail-Joon Ahn

AAMAS, 2016

⌛ Past life

Application of worker-manager model to genomic networks for identifying key regulators in Glioblastoma

worked with Debarka Sengupta and Sangamitra Bandhopadhyay

An improved fuzzy clustering method using modified Fukuyama-Sugeno cluster validity index

Sailik Sengupta, Soham De, Amit Konar, R. Janarthanan

ReTIS, 2010


Awards and Services

Projects and Other Stuff