Radu Grigore

Radu Grigore, Dino Distefano, Rasmus Lerchedahl Petersen et al.

We propose TOPL automata as a new method for runtime verification of systems with unbounded resource generation. Paradigmatic such systems are object-oriented programs which can dynamically generate an unbounded number of fresh object identities during their execution. Our formalism is based on register automata, a particularly successful approach in automata over infinite alphabets which administers a finite-state machine with boundedly many input-storing registers. We show that TOPL automata are equally expressive to register automata and yet suitable to express properties of programs. Compared to other runtime verification methods, our technique can handle a class of properties beyond the reach of current tools. We show in particular that properties which require value updates are not expressible with current techniques yet are naturally captured by TOPL machines. On the practical side, we present a tool for runtime verification of Java programs via TOPL properties, where the trade-off between the coverage and the overhead of the monitoring system is tunable by means of a number of parameters. We validate our technique by checking properties involving multiple objects and chaining of values on large open source projects.

Radu Grigore, Hongseok Yang

The core challenge in designing an effective static program analysis is to find a good program abstraction -- one that retains only details relevant to a given query. In this paper, we present a new approach for automatically finding such an abstraction. Our approach uses a pessimistic strategy, which can optionally use guidance from a probabilistic model. Our approach applies to parametric static analyses implemented in Datalog, and is based on counterexample-guided abstraction refinement. For each untried abstraction, our probabilistic model provides a probability of success, while the size of the abstraction provides an estimate of its cost in terms of analysis time. Combining these two metrics, probability and cost, our refinement algorithm picks an optimal abstraction. Our probabilistic model is a variant of the Erdos-Renyi random graph model, and it is tunable by what we call hyperparameters. We present a method to learn good values for these hyperparameters, by observing past runs of the analysis on an existing codebase. We evaluate our approach on an object sensitive pointer analysis for Java programs, with two client analyses (PolySite and Downcast).

Radu Grigore

This dissertation discusses several problems loosely related, because they all involve a verification condition generator. The Boogie language is introduced; the architecture of a verification-generator is described. Then come more interesting parts. (1) Moving to a passive form representation can be seen as an automatic transformation into a pure functional language. How to formalize this transformation and what is its complexity? (2) How do various ways of describing the semantics of procedural languages (predicate transformers, operational semantics) relate to each other? (3) How to do incremental verification? That is, how to work less when re-verifying a program that changed only a little since the verifier was last run. (4) How to detect unreachable code, taking into account formal specifications?