Hi! I'm a Junior at MIT thinking about 1) planning and learning in robotics and 2) AI security and safety.
I'm really proud of EvoGym, a tool for soft robot design and control co-optimization which I built with CDFG @ MIT. EvoGym was featured in Scientific American, Wired, Forbes, IEEE Spectrum, and MIT News!
- planning and learning for robotics
- AI systems security
Accepted position as Machine Learning Researcher @ Scale AI for Summer ‘22.
Building A Tool for Soft Robot Design and Control Co-optimization
Evolution Gym is the first benchmark tool for studying soft robot co-optimization: jointly optimizing a robot’s body and brain. We built EvoGym to have 1) A fast soft-body simulator 2) OpenAI Gym inspired python interface and 3) over 30 environments in order to overcome the prior intractability and irreproducibility of soft robot co-design experiments. In addition, we proposed 3 SOTA co-design algorithms and benchmarked them extensively on all EvoGym environments to establish baseline performance in this field. We hope EvoGym will lead to the development of increasingly intelligent robots! Code and extensive docs are available!
Breaking Apple's NeuralHash through Approximate Linearity
Presented at the 2022 ML4Cyber workshop at ICML.
Perceptual hashes map images with identical semantic content to the same n-bit hash value, and otherwise assign images to different hashes. Apple’s NeuralHash is one such system aiming to detect illegal content on users’ devices without compromising consumer privacy. We make the surprising discovery that NeuralHash is approximately linear, which inspired the development of novel black-box attacks that can (i) evade detection of ‘illegal’ images, (ii) generate near-collisions, and (iii) leak information about hashed images, all without access to model parameters. These vulnerabilities pose serious threats to NeuralHash’s security goals; to address them, we propose a simple fix using classical cryptographic standards.
Improving Machine Learning Algorithms for PAC Learning
We designed and analyzed novel, simple, and efficient algorithms for interactively learning non-binary concepts in the learning from random counter-examples (LRC) model. Here, learning takes place from random counter-examples that the learner receives in response to their proper equivalence queries, and the learning time is the number of counter-examples needed by the learner to identify the target concept. Such learning is particularly suited for online ranking, classification, clustering, etc., where machine learning models must be used before they are fully trained.
3D Modular Origami
Fold. Crease. Fold. Shape. Repeat. Each model is made with anywhere from 100-1000 individually crafted pieces. It’s time-consuming, but also quite relaxing!
LED Display Board
My first ever project in a MIT makerspace! The display is a 30x10 grid of individually addressable WS2812B LEDs controlled by an Arduino UNO – meaning I can display nearly any low-res image or gif. It’s facing the street from my New Vassar window for all of MIT to see :D