Vishnu Asutosh Dasu
vdasu at psu dot edu

I am a master's student in computer science (MS CSE) at the Pennsylvania State University. I am advised by Prof. Gary Tan and work on improving the fairness of ML algorithms along with Prof. Saeid Tizpaz-Niari. I also collaborate with Prof. Shagufta Mehnaz on data extraction attacks from LLMs trained using federated learning. Additionally, as a researcher at OpenMined Research, I also work with Prof. Ferdinando Fioretto on the fairness and robustness of LLMs.

Prior to joining Penn State, I worked at Tata Consultancy Services (TCS) Research as a Researcher in the Cybersecurity and Privacy Division. There, I worked with Prof. Sumanta Sarkar on privacy-preserving federated learning and insider threat and anomaly detection.

I received my bachelors degree in computer science from Manipal Institute of Technology, India in 2020. During my bachelors, I worked as a researcher at Nanyang Technological University (NTU), Singapore where I was advised by Prof. Anupam Chattopadhyay and Dr. Anubhab Baksi. I also worked as a research intern at TCS Research with Dr. Chalamala Srinivasa Rao on adversarial defenses and explainable AI.

In addition to my work as an academic, I worked in the industry as a software development intern at Citrix R&D and as a machine learning intern at Tiny Banyan Technologies (ML startup).

CV  /  Resume  /  Research Summary  /  Resume (1 Page)  /  Google Scholar  /  LinkedIn  /  Twitter  /  GitHub

My Erdős number is 4: Paul Erdős → Israel Koren → Francesco Regazzoni → Takanori Isobe → Vishnu Asutosh Dasu

I would love to collaborate with like-minded researchers and am open to opportunities. Please reach out to me if you're interested!

In the past, I have worked on a plethora of topics in cybersecurity, cryptography, and ML such as logic synthesis of block ciphers, ML-assisted differential cryptanalysis, and ML-assisted side channel attacks. Currently, I am interested in Trustworthy ML. This includes topics such as privacy-preserving ML, adversarial attacks/defenses, fair and bias free ML, explainable AI, and machine unlearning. A brief summary of my research experience and publications can be found here.

We introduce two novel privacy leakage attacks against federated language models. First, we show that intermediate model snapshots can leak more sensitive data than the final trained model. Second, we show that tampering with a model's selective weights responsible for memorizing sensitive data can aggravate privacy leakage. Our best-performing method outperforms existing attacks with stronger adversary assumptions.

EvoquerBot is a multimedia chatbot developed for the TaskBot challenge, aimed at assisting users with cooking and DIY tasks in a single session. The bot addresses challenges like short development time, data quality, multimedia responses, and tailored conversation flow using agile classifier development, data augmentation, multimedia response design, and domain-specific dialogue state machines, ultimately improving user experience through superior task recommendations.

We show new machine learning differential distinguishers for unkeyed and round-reduced versions of SPECK-32, SPECK-128, ASCON, SIMECK-32, SIMECK-64, and SKINNY-128. Our comprehensive experiments utilize neural networks and support vector machines in various settings and numerous input difference tuples.

We propose PROV-FL, a secure and private federated learning protocol. PROV-FL utilizes homomorphic encryption and differential privacy to provide strong privacy guarantees. It is resilient to user dropouts/joins, supports verifiable aggregation, and requires only a single round of communication without a full-trusted third party.

We propose an end-to-end solution to perform SCA on stream ciphers by combining automated tools such as ML, MILP, and SMT. We demonstrate its efficacy by taking electromagnetic traces from a 32-bit software platform and performing SCA on the TRIVIUM stream cipher.

We reproduce the results and validate the claims presented in GANSpace: Discovering Interpretable GAN Controls.

We develop a method to extend the Boyar-Peralta's algorithm to use XOR3 gates, add XOR3 gates to existing XOR2 implementations, and show several SOTA results on the linear layers of block ciphers using different logic libraries.

We develop automated tools using SMT and MILP techniques to generate low cost implementations of the linear layers used in ciphers.

We present an extension of the Boyar-Peralta's algorithm to generate implementations of linear layes using XOR2 and XOR3 gates. We show new results on the AES MixColumn matrix using XOR3 gates.

We develop a framework that extends LIGHTER to add support for generating optimized implementations of 4x4 SBoxes using reversible logic libraries.

1. TCS Citation Award (3-time Recipient): Received the TCS Citation Award and appreciation from the Chief Technical Officer and Head of TCS Research thrice for performance and outstanding contribution to the organization.
2. Scholarship: Received a scholarship to attend the Winter School on Responsible AI in The Dead Sea, Israel.
3. Best Project Award: Received the Best Project Award among 13 teams during the Fifth Summer School on Computer Vision, Graphics and Image Processing, Indian Statistical Institute (ISI) Kolkata.
4. IGVC: Placed 2nd in the Interoperability Profiles Challenge and 9th overall at Intelligent Ground Vehicle Competition (IGVC) 2018 among 26 teams. Second-best among all teams from India.
5. ACM ICPC Regionals: Represented Manipal Institute of Technology, Manipal at the 2017 ACM ICPC Asia Regional Contest.
6. DAGsHub Award: Received a $500 award from DAGsHub for successfully reproducing GANSpace: Discovering Interpretable GAN Controls and completing the ML Reproducibility Challenge Spring 2021.

• Reviewer for ReScience, 2022 -

We develop a technique to determine the 3D coordinates of a human from a live video feed using a camera with a single lens (monocamera setup).

I enjoy powerlifitng, playing the guitar, and reading about history, theology, and philosophy.