Hyperproperties are properties that relate multiple execution traces.
Pr...
As AI and machine-learned software are used increasingly for making deci...
Machine-learned systems are in widespread use for making decisions about...
A machine-learned system that is fair in static decision-making tasks ma...
We explore the notion of history-determinism in the context of timed aut...
Safety and liveness are elementary concepts of computation, and the
foun...
We study the problem of training and certifying adversarially robust
qua...
We study the problem of learning controllers for discrete-time non-linea...
We consider the problem of learning control policies in stochastic syste...
There is an ever-growing zoo of modern neural network models that can
ef...
Residual mappings have been shown to perform representation learning in ...
In this work, we address the problem of learning provably stable neural
...
Adversarial training (i.e., training on adversarially perturbed input da...
We consider the problem of formally verifying almost-sure (a.s.) asympto...
Bayesian neural networks (BNNs) place distributions over the weights of ...
We introduce a new stochastic verification algorithm that formally quant...
In runtime verification, a monitor watches a trace of a system and, if
p...
Information-flow policies prescribe which information is available to a ...
Adversarial training is an effective method to train deep learning model...
Formal verification of neural networks is an active topic of research, a...
Machine-learning techniques achieve excellent performance in modern
appl...
Machine learning and formal methods have complimentary benefits and
draw...
Contract-based design is a promising methodology for taming the complexi...
Neural networks have demonstrated unmatched performance in a range of
cl...
The monitoring of event frequencies can be used to recognize behavioral
...
In two-player games on graphs, the players move a token through a graph ...
In two-player games on graphs, the players move a token through a graph ...
Model-based testing is a promising technology for black-box software and...
In two-player games on graphs, the players move a token through a graph ...
Planning in adversarial and uncertain environments can be modeled as the...