We present AI 2, the first sound and scalable analyzer for deep neural networks. Based on
overapproximation, AI 2 can automatically prove safety properties (eg, robustness) of …

Unlike coverage-based fuzzing that gives equal attention to every part of a code, directed
fuzzing aims to direct a fuzzer to a specific target in the code, eg, the code with potential …

Inductive invariants can be robustly synthesized using a learning model where the teacher is
a program verifier who instructs the learner through concrete program configurations …

We introduce ICE, a robust learning paradigm for synthesizing invariants, that learns using
examples, counter-examples, and implications, and show that it admits honest teachers and …

We extend the data-driven approach to inferring preconditions for code from a set of test
executions. Prior work requires a fixed set of features, atomic predicates that define the …

A constraint-based approach to invariant generation in programs translates a program into
constraints that are solved using off-the-shelf constraint solvers to yield desired program …

The success of software verification depends on the ability to find a suitable abstraction of a
program automatically. We propose a method for automated abstraction refinement which …

Neural networks are becoming increasingly prevalent in software, and it is therefore
important to be able to verify their behavior. Because verifying the correctness of neural …

Symbolic complexity bounds help programmers understand the performance characteristics
of their implementations. Existing work provides techniques for statically determining bounds …

This paper discusses our methodology for formal analysis and automatic verification of
software programs. It is applicable to a large subset of the C programming language that …