Abbas Yazdinejad – The Conversation

The important part of memory poisoning is the delay, as a poisoned AI agent may not immediately behave like a compromised system. (Unsplash/Xavier Cee)

September 3, 2026

AI agents can now remember and hackers can ‘poison’ their memories — a new cybersecurity threat

Abbas Yazdinejad, University of Regina

Memory makes AI agents more useful, but it can also allow malicious instructions to remain hidden and influence decisions long after an attack.

Meta’s Stanton Springs Data Center, which supports AI and digital services, is visible Jan. 13, 2026, in Newton County, Ga. (AP Photo/Mike Stewart)

April 13, 2026

Does ‘federated unlearning’ in AI improve data privacy, or create a new cybersecurity risk?

Abbas Yazdinejad, University of Regina and Ann Fitz-Gerald, Balsillie School of International Affairs

As governments push for stronger data rights like the “right to be forgotten,” evidence suggests AI may not fully comply, raising new regulatory challenges.

In health care, generative AI offers welcome relief by automating documentation and translation, yet its unchecked use in health settings could erode public trust in medical data protection. (Unsplash/Vitaly Gariev)

November 18, 2025

Silent cyber threats: How shadow AI could undermine Canada’s digital health defences

Abbas Yazdinejad, University of Regina and Jude Kong, University of Toronto

Shadow AI is the unsanctioned use of AI systems without formal institutional oversight. In health care, it means pasting patient details into public chatbots.

This image made a fake video featuring former President Barack Obama shows elements of facial mapping used in new technology that lets anyone make videos of real people appearing to say things they’ve never said. (AP Photo)

August 20, 2025

Battling deepfakes: How AI threatens democracy and what we can do about it

Abbas Yazdinejad, University of Regina and Jude Kong, University of Toronto

Open-source generative AI tools and certain apps put audio and video manipulation in the hands of anyone with a laptop. Here’s why that poses such a dire threat to democracy.

Canada’s new minister of artificial intelligence, Evan Solomon speaks during the Canada 2020 conference in Ottawa on June 10, 2025. THE CANADIAN PRESS/Spencer Colby

June 12, 2025

Mitigating AI security threats: Why the G7 should embrace ‘federated learning’

Abbas Yazdinejad, University of Regina and Jude Kong, University of Toronto

Federated learning offers a new foundation for AI — one where privacy, transparency and innovation can move together.

Contact Abbas for