Aman Priyanshu

AI Safety & Privacy Researcher

Hi, I'm Aman!

I'm an AI Researcher at Cisco specializing in AI safety, security, and privacy leakages in AI systems. In my brief time as a researcher, I've been fortunate to publish in various AI conferences, journals, and workshops, with my work spanning privacy-preserving machine learning, AI security, and large language models. My focus has been on uncovering vulnerabilities in foundation models - work that has garnered media attention (1, 2, 3) and led to invitations to join some really cool security initiatives like OpenAI's Red Teaming Network and Anthropic's Model Safety Bug Bounty Program (though couldn't participate completely due to student-visa restrictions).

With a Masters in Privacy Engineering from Carnegie Mellon University, I've worked closely with Professor Norman Sadeh on LLMs and cybersecurity research, while also collaborating externally with Professor Ashique KhudaBukhsh (RIT) on exploring LLM political polarization and jailbreak-assisted toxic rabbit hole evaluations. My contributions to privacy-preserving machine learning and AI safety have been recognized through the AAAI Undergraduate Consortium Scholar and MITACS Research Scholar awards, further fueling my passion for bridging the gap between theoretical vulnerabilities and real-world implications.

Aman Priyanshu

Media Coverage & Features

scrollable: please scroll left or right →

Publications

2024

Through the Lens of LLMs: Unveiling Differential Privacy Challenges

Aman Priyanshu, Yash Maurya, Vy Tran, Suriya Ganesh Ayyamperumal

USENIX Conference on Privacy Engineering Practice and Respect

2023

Guarding Your Social Circle: Strategies to Protect Key Connections and Edge Importance

Nisha P Shetty, Balachandra Muniyal, Akshat Dokania, Sohom Datta, Manas Subramanyam Gandluri, Leander Melroy Maben, Aman Priyanshu

Security and Communication Networks

2023

FedBully: A Cross-Device Federated Approach for Privacy Enabled Cyber Bullying Detection using Sentence Encoders

Nisha P Shetty, Balachandra Muniyal, Aman Priyanshu, Vedant Rishi Das

Journal of Cyber Security and Mobility

2023

Are Chatbots Ready for Privacy-Sensitive Applications? An Investigation into Input Regurgitation and Prompt-Induced Sanitization

Aman Priyanshu, Supriti Vijay, Ayush Kumar, Rakshit Naidu, Fatemehsadat Mireshghallah

Pre-Print (In-Submission)

2022

#maskUp: Selective Attribute Encryption for Sensitive Vocalization for English language on Social Media Platforms

Aman Priyanshu, Supriti Vijay

Research & Reports Track at #ShowYourSkill, Coursera

2022

NERDA-Con: Extending NER models for Continual Learning - Integrating Distinct Tasks and Updating Distribution Shifts

Supriti Vijay, Aman Priyanshu

Updatable Machine Learning Workshop, ICML 2022

2022

ARLIF-IDS: Attention augmented Real-Time Isolation Forest Intrusion Detection System

Aman Priyanshu, Sarthak Shastri, Sai Sravan Medicherla

43rd IEEE Symposium on Security and Privacy

2022

Finding an elite feature for (D)DoS fast detection-Mixed methods research

Josy Elsa Varghese, Balachandra Muniyal, Aman Priyanshu

Computers & Electrical Engineering, Volume 98

2021

Efficient Hyperparameter Optimization for Differentially Private Deep Learning

Aman Priyanshu, Rakshit Naidu, Fatemehsadat Mireshghallah, Mohammad Malekzadeh

Privacy Preserving Machine Learning Workshop, ACM CCS 2021

2021

Something Something Hota Hai! An Explainable Approach towards Sentiment Analysis on Indian Code-Mixed Data

Aman Priyanshu, Aleti Vardhan, Sudarshan Sivakumar, Supriti Vijay, Nipuna Chhabra

Workshop on Noisy User-generated Text (W-NUT), EMNLP 2021

2021

When Differential Privacy Meets Interpretability: A Case Study

Rakshit Naidu, Aman Priyanshu, Aadith Kumar, Sasikanth Kotti, Haofan Wang, Fatemehsadat Mireshghallah

Responsible Computer Vision Workshop, CVPR 2021 & Privacy Preserving Machine Learning Workshop, ACM CCS 2021

2021

Continual Distributed Learning for Crisis Management

Aman Priyanshu, Mudit Sinha, Shreyans Mehta

3rd Workshop on Continual and Multimodal Learning for Internet of Things, IJCAI 2021

2021

FedPandemic: A Cross-Device Federated Learning Approach Towards Elementary Prognosis of Diseases During a Pandemic

Aman Priyanshu, Rakshit Naidu

Machine Learning for Preventing and Combating Pandemics & Distributed and Private Machine Learning Workshops, ICLR 2021

2020

Stance Classification with Improved Elementary Classifiers Using Lemmatization (Grand Challenge)

Aman Priyanshu, Vedant Rishi Das, Shashank Rajiv Moghe, Harsh Rathod, Sai Sravan Medicherla, Mini Shail Chhabra, Sarthak Shastri

IEEE Sixth International Conference on Multimedia Big Data (BigMM)

Curated Blogs

scrollable: please scroll left or right →

Experience

AI Security Research Intern

Robust Intelligence

Jun 2024 - Aug 2024

Founding Member & AI-Lead

MyCelium Sports (Course: 11-681)

Jan 2024 - May 2024

Privacy Engineering Independent Study

Under Professor Norman Sadeh at CMU

Aug 2023 - Apr 2024

Research Project Lead & Contributor

OpenMined

Mar 2023 - Aug 2023

AAAI Undergraduate Consortium Scholar

The Association for the Advancement of Artificial Intelligence

Feb 2023

Co-Founder

Felasa Initiative (Open-Source Women's Safety Awareness Initiative)

Aug 2022 - Present

Privacy Engineer Intern

Eder Labs R&D Private Limited, Delaware, USA

Aug 2022 - Aug 2023

MITACS Research Intern

Concordia University, Quebec, Canada

May 2022 - Aug 2022

Federated Learning Intern

DynamoFL, California, USA

March 2022 - May 2022

Undergraduate Research Assistant

Manipal Institute of Technology, Karnataka, India

May 2021 - Jun 2023

Expertise Sub-Head, Artificial Intelligence

Research Society Manipal, Karnataka, India

Feb 2021 - Dec 2022

Technical Head

Cryptonite Student Project

June 2021 - Dec 2022

Machine Learning and Web Crawling Intern

Oniria Pets, Poland

Jan 2020 - Feb 2020

Education

Carnegie Mellon University

MSIT in Privacy Engineering

Key Courses: Prompt Engineering (17730), AI Governance (17716), Deep Learning (11785), Computer Technology Law (17562), Differential Privacy (17731), Information Security (17631), & Usability (17734)

Manipal Institute of Technology

B.Tech in Information Technology

Key Courses: Data Structures and Algorithms, Design and Analysis of Algorithms, Object Oriented Programming, Probability and Statistics, Computer Networks, Operating Systems, Database Management

Relevant Projects

ProTaska-GPT

June 2023

Specify your dataset of choice, and ProTaska-GPT will understand the dataset with tasks, tutorials, and actionable insights for it. Accelerate your data science journey with ease and efficiency! (Meant for people starting their journey into Data Science.)

AdaptKeyBERT

October 2022

Built a python library, integrating semi-supervised attention for creating a few-shot & zero-shot domain adaptation technique for keyphrase extraction.

DP-SDV

June 2022

Creating a Differential Privacy securing Synthetic Data Generation for tabular, relational and time series data.

NERDA-Con

May 2022

NERDA-Con is a python package, a pipeline for training Named Entity Recognition (NER) with Large Language Models bases by incorporating the concept of Elastic Weight Consolidation (EWC) into the NER fine-tuning NERDA pipeline.

DP-HyperparamTuning

August 2021

DP-HyperparamTuning offers an array of tools for fast and easy hypertuning of various hyperparameters for the DP-SGD algorithm. We proposed a novel, customizable reward function that allows users to define a single objective function for establishing their desired privacy-utility tradeoff.

Hexa Lite

August 2021

Created an unsupervised machine learning to extract contextually similar texts. The project was used in indexing Academic Literature, Law Precedents, and Financial Records. The project won Code Innovation Series - a Hackathon in association with GitHub.

Augmented Face Detection API

July 2021

The app performs obstruction detection, spoof detection, blur detection and environment approval. Utilized Deep Neural Networks and Genetic Algorithms to achieve these goals in low computational time. The project won 1st place in HackRx 2.0 by Bajaj Finserv.

DeCrise

May 2021

DeCrise is an online platform that acts as an aggregator for public support/utility services which uses continual-federated-learning to create a quick response information retrieval system during a natural disaster. The project won 1st place in The ACM UCM Datathon.

Voix

April 2021

A social-media platform employing machine learning and differential privacy to promote civic engagement while protecting user-privacy. The project won under the Community & Civic Engagement for UC Berkeley's CalHacks Hackathon.

Achievements

Spark Grant Winner - NOVA Hacks

March 2024

Won the Spark Grant for our app that enhances speech for non-native English speakers, employing prompt-engineering function-calling (OpenAI GPT4/3.5) and Speech-to-Text (OpenAI Whisper), with features like audio-segmentation, speaker-recognition, and diarization.

Space Theme Category Winner - HackCMU

September 2023

Won the Space-Themed track with our space trash collection project using Pareto optimization to balance time, fuel requirements, satellite movements, planetary alignment, and the trajectory of trash collectors for predicting monetary incentives.

Research & Travel Grant - AAAI Undergraduate Consortium Scholar

February 2023

Selected as one of twelve individuals for the AAAI UC program, recognizing my research on Privacy and Fairness.

Second Runners-Up - ShowYourSkill (Coursera)

June 2022

Came second runners-up in #ShowYourSkill where we participated in the Research & Reports Track and creating a NLP augmented Machine Learning Application for women safety.

Runners-Up - BobHacks 2021

September 2021

Came runners-up in BobHacks where we built a pattern recognition API built on top of the MetaBob API. The API is able to assist users in tracking common errors and delivers pattern recognition on the MetaBob API.

First Prize - Code Innovation Series

August 2021

Innovation Series Hackathon was organized by Manipal Institute of Technology. Employed Document-Embedding for measuring contextual similarity between multiple pages and given search-queries.

First Prize - HackRx by Bajaj Finserv

July 2021

Used Deep Learning and Classical Image processing to achieve a face verification and profile-rank estimation task. The methodology out-performed classic Deep Learning methods.

First Prize - ACM UCM Datathon

May 2021

Built DeCrise, an online platform that acts as an aggregator for public support/utility services for fast-response during a major crisis or disaster.

First Prize - CalHacks Hackathon

April 2021

Won under the Community & Civic Engagement track. Built Voix, an anonymous platform for uplifting communities and promoting civic participation using privacy-enabled machine learning.

Runners-Up - Furniture Identification

September 2020

Employed skip-connections to generate high-performance model for furniture identification in IECSE x VISION competition.

Runners-Up - IEEE BigMM Data Challenge

August 2020

Came runners-up in IEEE Grand-Challenge for harassment detection on tweets. Used Elementary Classifiers for Sentiment Analysis. The team was invited to present at IEEE BigMM conference.

Intel Edge AI Scholarship Recipient

January 2020

Selected as one of the recipients of the Intel Edge AI Scholarship Program. Learned about Machine Learning Implementation on the Edge.

Interactive Tools/Demos & Games

scrollable: please scroll left or right →