Speranza: Usable, privacy-friendly software signing
Software repositories, used for wide-scale open software distribu- tion, are a significant vector for security attacks. Software signing provides authenticity, mitigating many such attacks. Developer- managed signing keys ...
MIT Computer Science and Artificial Intelligence Lab (CSAIL)How Can Large Language Models Help Humans in Design And Manufacturing?
MIT Computer Science and Artificial Intelligence Lab (CSAIL)Counterfactual Explanations and Predictive Models to Enhance Clinical Decision-Making in Schizophrenia using Digital Phenotyping
Clinical practice in psychiatry is burdened with the increased demand for healthcare services and the scarce resources available. New paradigms of health data powered with machine learning techniques could open the possibility ...
MIT Computer Science and Artificial Intelligence Lab (CSAIL)Automated Exposure Notification for COVID-19
Private Automated Contact Tracing (PACT) was a collaborative team and effort formed during the beginning of the Coronavirus Disease 2019 (COVID-19) pandemic. PACT’s mission was to enhance contact tracing in pandemic response ...
MIT Computer Science and Artificial Intelligence Lab (CSAIL)Neurosymbolic Programming for Science
Neurosymbolic Programming (NP) techniques have the potential to accelerate scientific discovery across fields. These models combine neural and symbolic components to learn complex patterns and representations from data, ...
MIT Computer Science and Artificial Intelligence Lab (CSAIL)Universal Motion Generator: Trajectory Autocompletion by Motion Prompts
Foundation models, which are large neural networks trained on massive datasets, have shown impressive generalization in both the language and the vision domain. While fine-tuning foundation models for new tasks at test-time ...
MIT Computer Science and Artificial Intelligence Lab (CSAIL)Active Loop Detection for Applications that Access Databases
We present Shear, a new system that observes and manipulates the interaction between an application and its surrounding environment to learn a model of the behavior of the application. Shear implements active loop detection ...
MIT Computer Science and Artificial Intelligence Lab (CSAIL)Active Loop Detection for Applications that Access Databases
We present Shear, a new system that observes and manipulates the interaction between an application and its surrounding environment to learn a model of the behavior of the application. Shear implements active loop detection ...
MIT Computer Science and Artificial Intelligence Lab (CSAIL)Active Loop Detection for Applications that Access Databases
We present Shear, a new system that observes and manipulates the interaction between an application and its surrounding environment to learn a model of the behavior of the application. Shear implements active loop detection ...
MIT Computer Science and Artificial Intelligence Lab (CSAIL)Bucket Elimination Algorithm for Dynamic Controllability Checking of Simple Temporal Networks with Uncertainty
Simple Temporal Networks with Uncertainty (STNU) can represent temporal problems where duration between events may be uncontrollable, e.g. when the event is caused by nature. An STNU is dynamically controllable (DC) if it ...
MIT Computer Science and Artificial Intelligence Lab (CSAIL)Lower Bounds on the Column Sparsity of Compressed Sensing Matrices
MIT Computer Science and Artificial Intelligence Lab (CSAIL)Bucket Elimination Algorithm for Dynamic Controllability Checking of Simple Temporal Networks with Uncertainty
Simple Temporal Networks with Uncertainty (STNU) can represent temporal problems where duration between events may be uncontrollable, e.g. when the event is caused by nature. An STNU is dynamically controllable (DC) if it ...
MIT Computer Science and Artificial Intelligence Lab (CSAIL)Precise and Comprehensive Provenance Tracking for Android Devices
Detailed information about the paths that data take through a system is invaluable for understanding sources and behaviors of complex exfiltration malware. We present a new system, ClearScope, that tracks, at the level of ...
MIT Computer Science and Artificial Intelligence Lab (CSAIL)Comprehensive Java Metadata Tracking for Attack Detection and Repair
We present ClearTrack, a system that tracks 32 bits of metadata for each primitive value in Java programs to detect and nullify a range of vulnerabilities such as integer overflow and underflow vulnerabilities, SQL injection ...
MIT Computer Science and Artificial Intelligence Lab (CSAIL)Faster Dynamic Controllability Checking in Temporal Networks with Integer Bounds
Simple Temporal Networks with Uncertainty (STNUs) provide a useful formalism with which to reason about events and the temporal constraints that apply to them. STNUs are in particular notable because they facilitate reasoning ...
MIT Computer Science and Artificial Intelligence Lab (CSAIL)Automatic Exploitation of Fully Randomized Executables
We present Marten, a new end to end system for automatically discovering, exploiting, and combining information leakage and buffer overflow vulnerabilities to derandomize and exploit remote, fully randomized processes. ...
MIT Computer Science and Artificial Intelligence Lab (CSAIL)Gen: A General-Purpose Probabilistic Programming System with Programmable Inference
Probabilistic modeling and inference are central to many fields. A key challenge for wider adoption of probabilistic programming languages is designing systems that are both flexible and performant. This paper introduces ...
MIT Computer Science and Artificial Intelligence Lab (CSAIL)Towards Understanding Generalization via Analytical Learning Theory
This paper introduces a novel measure-theoretic theory for machine learning that does not require statistical assumptions. Based on this theory, a new regularization method in deep learning is derived and shown to ...
MIT Computer Science and Artificial Intelligence Lab (CSAIL)Using Dynamic Monitoring to Synthesize Models of Applications That Access Databases
We previously developed Konure, a tool that uses active learning to infer the functionality of database applications. An alternative approach is to observe the inputs, outputs, and database traffic from a running ...
MIT Computer Science and Artificial Intelligence Lab (CSAIL)Using Active Learning to Synthesize Models of Applications That Access Databases
We present a new technique that uses active learning to infer models of applications that manipulate relational databases. This technique comprises a domain-specific language for modeling applications that access ...
MIT Computer Science and Artificial Intelligence Lab (CSAIL)Best-first Enumeration Based on Bounding Conflicts, and its Application to Large-scale Hybrid Estimation
With the rise of autonomous systems, there is a need for them to have high levels of robustness and safety. This robustness can be achieved through systems that are self-repairing. Underlying this is the ability to diagnose ...
MIT Computer Science and Artificial Intelligence Lab (CSAIL)Learning Models of Sequential Decision-Making without Complete State Specification using Bayesian Nonparametric Inference and Active Querying
Learning models of decision-making behavior during sequential tasks is useful across a variety of applications, including human-machine interaction. In this paper, we present an approach to learning such models within ...
MIT Computer Science and Artificial Intelligence Lab (CSAIL)Generating Component-based Supervised Learning Programs From Crowdsourced Examples
We present CrowdLearn, a new system that processes an existing corpus of crowdsourced machine learning programs to learn how to generate effective pipelines for solving supervised machine learning problems. CrowdLearn uses ...
MIT Computer Science and Artificial Intelligence Lab (CSAIL)An Efficient Fill Estimation Algorithm for Sparse Matrices and Tensors in Blocked Formats
Tensors, linear-algebraic extensions of matrices in arbitrary dimensions, have numerous applications in computer science and computational science. Many tensors are sparse, containing more than 90% zero entries. Efficient ...
MIT Computer Science and Artificial Intelligence Lab (CSAIL)Multi-Unit Auction Revenue with Possibilistic Beliefs
The revenue of traditional auction mechanisms is benchmarked solely against the players' own valuations, despite the fact that they may also have valuable beliefs about each other's valuations. Not much is known about ...
MIT Computer Science and Artificial Intelligence Lab (CSAIL)Inference and Regeneration of Programs that Store and Retrieve Data
As modern computation platforms become increasingly complex, their programming interfaces are increasingly difficult to use. This complexity is especially inappropriate given the relatively simple core functionality that ...
MIT Computer Science and Artificial Intelligence Lab (CSAIL)Collaborative Diagnosis of Over-Subscribed Temporal Plans
Over-subscription, that is, being assigned too many tasks or requirements that are too demanding, is commonly encountered in temporal planning problems. As human beings, we often want to do more than we can, ask for things ...
MIT Computer Science and Artificial Intelligence Lab (CSAIL)Alpenhorn: Bootstrapping Secure Communication without Leaking Metadata
Alpenhorn is the first system for initiating an encrypted connection between two users that provides strong privacy and forward secrecy guarantees for metadata (i.e., information about which users connected to each other) ...
MIT Computer Science and Artificial Intelligence Lab (CSAIL)Automatic Inference of Code Transforms and Search Spaces for Automatic Patch Generation Systems
We present a new system, Genesis, that processes sets of human patches to automatically infer code transforms and search spaces for automatic patch generation. We present results that characterize the effectiveness of the ...
MIT Computer Science and Artificial Intelligence Lab (CSAIL)Modeling Network User Behavior: Various Approaches
This project involves learning to predict users' mobility within the network topology. Topological mobility, as opposed to physical mobility, can be substantial as a user switches from LTE to wifi network, while moving ...
MIT Computer Science and Artificial Intelligence Lab (CSAIL)