Rajeev Alur

Verisig 2.0: Verification of Neural Network Controllers Using Taylor Model Preconditioning

Lecture notes in computer science · 2021 · 56 citations

Abstract This paper presents Verisig 2.0, a verification tool for closed-loop systems with neural network (NN) controllers. We focus on NNs with tanh/sigmoid activations and develop a Taylor-model-based reachability algorithm through Taylor model preconditioning and shrink wrapping. Furthermore, we provide a parallelized implementation that allows Verisig 2.0 to efficiently handle larger NNs than existing tools can. We provide an extensive evaluation over 10 benchmarks and compare Verisig 2.0 ag…

Verifying the Safety of Autonomous Systems with Neural Network Controllers

ACM Transactions on Embedded Computing Systems · 2020 · 49 citations

This article addresses the problem of verifying the safety of autonomous systems with neural network (NN) controllers. We focus on NNs with sigmoid/tanh activations and use the fact that the sigmoid/tanh is the solution to a quadratic differential equation. This allows us to convert the NN into an equivalent hybrid system and cast the problem as a hybrid system verification problem, which can be solved by existing tools. Furthermore, we improve the scalability of the proposed method by approxima…

Understanding the Effectiveness of Large Language Models in Detecting Security Vulnerabilities

2025-03-31 · 27 citations

Security vulnerabilities in modern software are prevalent and harmful. While automated vulnerability detection techniques have made promising progress, their scalability and applicability remain challenging. The remarkable performance of Large Language Models (LLMs), such as GPT-4 and CodeLlama, on code-related tasks has prompted recent works to explore if LLMs can be used to detect security vulnerabilities. In this paper, we perform a more comprehensive study by examining a larger and more dive…

A Framework for Transforming Specifications in Reinforcement Learning

Lecture notes in computer science · 2022 · 19 citations

Understanding the Effectiveness of Large Language Models in Detecting Security Vulnerabilities

arXiv (Cornell University) · 2023-11-16 · 12 citations

While automated vulnerability detection techniques have made promising progress in detecting security vulnerabilities, their scalability and applicability remain challenging. The remarkable performance of Large Language Models (LLMs), such as GPT-4 and CodeLlama, on code-related tasks has prompted recent works to explore if LLMs can be used to detect vulnerabilities. In this paper, we perform a more comprehensive study by concurrently examining a higher number of datasets, languages and LLMs, an…