This paper describes a way to improve the scalability of program synthes...
We introduce dataset multiplicity, a way to study how inaccuracies,
unce...
Neural networks are vulnerable to backdoor poisoning attacks, where the
...
Every program should always be accompanied by a specification that descr...
We consider the problem of establishing that a program-synthesis problem...
Datasets typically contain inaccuracies due to human error and societal
...
Machine learning models are vulnerable to data-poisoning attacks, in whi...
Modern programmable network switches can implement custom applications u...
We present Prognosis, a framework offering automated closed-box learning...
Datasets can be biased due to societal inequities, human biases,
under-r...
This paper addresses the problem of creating abstract transformers
autom...
We present a method for synthesizing recursive functions that satisfy bo...
Deep neural networks for natural language processing are fragile in the ...
This paper develops a new framework for program synthesis, called
semant...
We consider the problem of automatically establishing that a given
synta...
Deep neural networks for natural language processing tasks are vulnerabl...
In networks today, the data plane handles forwarding—sending a packet to...
Machine learning models are brittle, and small changes in the training d...
We consider the problem of synthesizing a program given a probabilistic
...
Proving Unrealizability for Syntax-Guided Synthesis
We consider the pr...
The goal of program repair is to automatically fix programs to meet a
sp...
Code analyzers such as ErrorProne and FindBugs detect code patterns
symp...
Recent advances in program synthesis offer means to automatically debug
...
With the range and sensitivity of algorithmic decisions expanding at a
b...
We explore the following question: Is a decision-making program fair, fo...