[paper] [arxiv] [poster] [code] Osbert Bastani, Rahul Sharma, Alex Aiken, Percy Liang. Automated Synthesis of Semantic Malware Signatures using Maximum Satisfiability. [paper] [ar Xiv] Osbert Bastani, Yani Ioannou, Leonidas Lampropoulos, Dimitrios Vytiniotis, Aditya Nori, Antonio Criminisi.Tags: Scarlet Ibis EssayDifferent Kinds Of Narrative EssayDissertation On MotivationA Good Man Is Hard To Find Essay OutlineNet Working CoursesWhat Should A Thesis Introduction ContainCrucible Theme Essay RevengeThesis Robots Meta Tags
I am a research assistant professor at the Department of Computer and Information Science at the University of Pennsylvania. I am broadly interested in machine learning and programming languages research.
at Stanford advised by Alex Aiken, and spent a year as a postdoc at MIT working with Armando Solar-Lezama. Verifiable Reinforcement Learning via Policy Extraction.
An interactive approach to mobile app verification. Specification inference using context-free reachability. Randomization, sums of squares, near-circuits, and faster real root counting.
Interactively verifying absence of explicit information flows in Android apps. [paper] [presentation] Osbert Bastani, Saswat Anand, Alex Aiken. [paper] [presentation] Osbert Bastani, Christopher Hillar, Dimitar Popov, Maurice Rojas.
Durham PDF Row Compression and Nested Product Decomposition of a Hierarchical Representation of a Quasiseparable Matrix, Mary Hudachek-Buswell PDF Algorithms for Viral Population Analysis, Nicholas Mancuso PDF Visualizing Spatio-Temporal data, Ayush Shrestha PDF Data Assimilation for Agent-Based Simulation of Smart Environment, Minghao Wang PDF Data Assimilation Based on Sequential Monte Carlo Methods for Dynamic Data Driven Simulation, Haidong Xue PDF HIV Drug Resistant Prediction and Featured Mutants Selection using Machine Learning Approaches, Xiaxia Yu PDF Maximum Energy Subsampling: A General Scheme For Multi-resolution Image Representation And Analysis, Yanjun Zhao PDF Scientific High Performance Computing (HPC) Applications On The Azure Cloud Platform, Dinesh Agarwal PDF A Framework for Discovery and Diagnosis of Behavioral Transitions in Event-streams, Arash Akhlaghi PDF Real-time Physics Based Simulation for 3D Computer Graphics, Xiao Chen PDF Coronary Artery Calcium Quantification in Contrast-enhanced Computed Tomography Angiography, Abinashi Dhungel PDF Maintaining Integrity Constraints in Semantic Web, Ming Fang PDF Data Collection and Capacity Analysis in Large-scale Wireless Sensor Networks, Shouling Ji PDF A Classification Framework for Imbalanced Data, Piyaphol Phoungphol PDF Viral Quasispecies Reconstruction Using Next Generation Sequencing Reads, Bassam A.
Tork PDF Collaborative Communication And Storage In Energy-Synchronized Sensor Networks, Mingsen Xu PDF Protein Tertiary Model Assessment Using Granular Machine Learning Techniques, Anjum A.
For such applications, there are many desirable correctness properties that machine learning models should satisfy, including safety, robustness, fairness, causality, and interpretability.
My work aims to address the following challenges: Osbert Bastani.
Keith Noah Snavely, Scene Reconstruction and Visualization from Internet Photo Collection.2008Krzysztof Gajos, Automatically Generating Personalized User Interface.
Tapan Parikh, Designing an Architecture for Delivering Mobile Information Services to the Rural Developing World.2007Lin Liao, Location-Based Activity Recognition.