View Proposal

---

Proposer

Ekaterina Komendantskaya

Title

Probabilistic Verification of AI

Goal

Description

As machine learning algorithms find their ways in safety-critical systems, such as autonomous cars, robot nurses, conversational agents, the question of ensuring their safety and security becomes important. At the same time, neural networks are known to be vulnerable to adversarial attacks --- a special kind of crafted inputs that cause unintended behaviour in trained neural networks. Due to these two factors, neural network verification has become a hot topic in both machine learning and verification communities. It is often described as one of the main challenges faced by computer science and engineering these days. Often, we cannot verify a property with certainty, but can verify it with some degree of probability. There are languages ad tools for Probabilistic verification, for example, PRISM or Probabilistic Prolog. You will study this area and implement your own toy examples using these methods. You will have a chance to collaborate with researchers in the lab for AI and Verification: LAIV.uk.

Resources

Background

Url

Difficulty Level

High

Ethical Approval

None

Number Of Students

3

Supervisor

Ekaterina Komendantskaya

Keywords

Degrees