Seyedali Mirjalili

THE WRITER IS A PROFESSOR OF ARTIFICIAL INTELLIGENCE, FACULTY OF BUSINESS AND HOSPITALITY AT TORRENS UNIVERSITY AUSTRALIA

Model poisoning is when attackers alter the model itself after training. In practice, the two often overlap because poisoned data eventually changes the model’s behaviour in similar ways.

The rising threat of ‘AI poisoning’

Despite the hype surrounding artificial intelligence, new studies show that the technology is far more fragile than it appears