HomepageData + AI Summit 2022 Logo
Watch on demand

Adversarial AI—The Nature of the Threat, Impacts, and Mitigation Strategies

On Demand

Type

  • Session

Format

  • Virtual

Track

  • Data Security and Governance

Industry

  • Public Sector

Difficulty

  • Intermediate

Duration

  • 40 min

Overview

Adversarial AI/ML is an emerging research area focused on the vulnerabilities of Artificial Intelligence (AI)/Machine Learning (ML) models to adversarial exploitation such as data poisoning, adversarial perturbations, inference, and extraction attacks. This research area is of particular interest to domains where AI/ML models play an essential role in the mission-critical decision-making processes. In this presentation, we will give a review of the four principal categories of Adversarial AI in the context of a data and machine learning lifecycle as well as the general adversarial intent. We will discuss each of the four principal areas (including the threat of deep fakes), supported by the relevant and interesting examples, and we will discuss the future implications of these. We will present in greater depth our research in Adversarial NLP methods, backed by specific data poisoning and adversarial perturbation example attacks on NLP classifiers.
We will conclude the presentation by discussing the current mitigation approaches and methods, and offer some general recommendations for how to best address and mitigate the vulnerabilities to adversarial exploits of AI/ML models.

Session Speakers

Edmon Begoli

Section Head / Distinguished Scientist

Oak Ridge National Laboratory (ORNL)

See the best of Data+AI Summit

Watch on demand