Ambar Pal

Ambar Pal
ambar at jhu dot edu

Office: 322, Clark Hall, JHU

About Me

I am a PhD student in the Computer Science Department at the Johns Hopkins University, where my advisors are René Vidal and Jeremias Sulam. I am affiliated with the Mathematical Institute for Data Science. Previously I obtained my Masters degree from JHU, and my Bachelors degree from from IIIT Delhi, both in Computer Science. My CV can be found here.

Research Interests

My research focusses on the theory and practice of Robustness in Machine Learning. My central philosophy is that incorporating structural constraints from data can efficiently mitigate vulnerabilities in current ML systems to malicious agents. On the theoretical side, I have built frameworks formalizing how exploiting structure in data (e.g., low-dimensionality) can lead to improved formal guarantees for robustness. On the practical side, I have demonstrated the utility of such data-driven constraints for systems for image classification, graph classification, and facial recognition.

I am an Amazon Fellow for 2023-24. I received the JHU MINDS Data Science Fellowship 3 times, for the years 2022, 2021 and 2019.


  • Adversarial Examples Might be Avoidable: The Role of Data Concentration in Adversarial Robustness [NeurIPS 2023] (to Appear)
    Ambar Pal, Jeremias Sulam, René Vidal
  • Poster to appear in [DeepMath 2023]

  • Understanding Noise-Augmented Training for Randomized Smoothing [TMLR 2023]
    Ambar Pal, Jeremias Sulam.
  • Shorter version in [DeepMath 2022], [AI-X Symposium 2023]

  • Certified Defenses Against Near-Subspace Unrestricted Adversarial Attacks [ECCVW 2022]
    Ambar Pal, René Vidal.
  • Poster in [SLowDNN 2023]

  • Identifying Physically Realizable Triggers for Backdoored Face Recognition Networks [ICIP 2021]
    Ankita Raj, Ambar Pal, Chetan Arora.

  • A Game Theoretic Analysis of Additive Adversarial Attacks and Defenses [NeurIPS 2020]
    Ambar Pal, René Vidal.

  • On the Regularization Properties of Structured Dropout [CVPR 2020]
    Ambar Pal, Connor Lane, René Vidal, Benjamin D. Haeffele.

  • Making Deep Neural Network Fooling Practical [ICIP 2018]
    Ambar Pal, Chetan Arora.

  • An Empirical Evaluation of Visual Question Answering for Novel Objects [CVPR 2017]
    Santhosh Kumar R, Ambar Pal, Gaurav Sharma, Anurag Mittal.


  • On Utilizing Relationships for Transferrable, Few-Shot Object Detection
    Ambar Pal, Arnau Ramisa, Amit Kumar K C, René Vidal.

  • Principled Attacks to Graph Neural Networks
    Ambar Pal, Julio Hurtado, Marcel Nassar, Nesreen K. Ahmed, René Vidal.

  • Cells in the Internet of Things
    Ayush Shah, H. B. Acharya, Ambar Pal.

  • The Internet of Things: Perspectives on Security from RFID and WSN
    Ayush Shah, Ambar Pal, H. B. Acharya.


  • [September 23] Check out our poster on Randomized Smoothing at the AI-X Symposium 2023.
  • [September 23] Our paper highlighting the important role of structure in data for adversarial robustness is accepted to NeurIPS 23
  • [August 23] I am selected as an Amazon AI2AI fellow!
  • [April 23] Our paper on understanding Randomized Smoothing in adversarial robustness is accepted to TMLR 2023
  • [Jan 23] I will be presenting our work on provable adversarial defenses for unrestricted attacks at SLowDNN 2023 in Abu Dhabi
  • [September 22] I will be attending the 2022 THEORINET Retreat in New York City.
  • [July 22] I will be speaking at Meta AI on adversarial robustness for small-norm and large-norm attacks.
  • [July 22] I will be speaking at Meta AI Research on our work on a game theoretic analysis of adversarial attacks and defenses.
  • [June 22] I will be at CVPR 2022 in wonderful New Orleans.
  • [May 22] I will be a research intern at Meta Research in Bellevue, Washington! I will be working with Mike Rabbat, Grey Yang, and Xing Wang.
  • [March 22] I will be speaking at the JHU MINDS retreat on a Game-Theoretic Analysis of Attacks and Defenses.
  • [Jan 22] I am honored to receive the 2022 MINDS Fellowship.
  • [July 21] Our paper on detecting physical backdoors in facial recognition systems is accepted at ICIP 2021. Congrats Ankita!
  • [May 21] I will be a research intern with the Amazon Visual Search team in Palo Alto, California! I will be working with Amit and Arnau.
  • [Oct 20] Our paper developing a game-theoretic framework for additive adversarial attacks and defenses is accepted at NeurIPS 2020! Check out the paper here
  • [Sep 20] Our work on adversarial learning is accepted for presentation at DeepMath 2020
  • [June 20] I will be speaking at the Pontifical Catholic University of Chile on Structured Dropout.

Past Life

In the past, I have been fortunate to have worked with several wonderful people on several exciting problems. Chetan Arora[IIT Delhi] was my undergraduate advisor, and we analysed the robustness of image classification and facial recognition models to various types of physically realizable adversarial perturbations. I interned with Yan Liu[USC] on the problem of survival prediction for cancer patients using machine learning. I worked with Gaurav Sharma at IIT Kanpur, where together with Santhosh we explored the limits of visual question answering. I have worked with H.B. Acharya[RIT] on classifying and identifying security aspects of the Internet of Things. With Somitra Sanadhya[IIT Ropar], I have explored and implemented differential attacks on the cryptographic hash function SHA-2. Finally, I have worked with Rajiv Raman[IIIT Delhi] on the planar support problem in discrete geometry.