menu_open Columnists
Abbas Yazdinejad

Abbas Yazdinejad

The Conversation

We use cookies to provide some features and experiences in QOSHE

More information  .  Close

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

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

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

03.09.2026 20

The Conversation

Abbas Yazdinejad

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

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

13.04.2026 40

The Conversation

Abbas Yazdinejad

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

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

19.11.2025 40

The Conversation

Abbas Yazdinejad

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

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...

20.08.2025 30

The Conversation

Abbas Yazdinejad

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

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

12.06.2025 30

The Conversation

Abbas Yazdinejad