Cybersecurity: AI attacks and hijacking

● AI and generative AI systems can be easily hijacked to generate malicious code, even when designed to reject such requests.
● Other types of attacks, known as "model evasion attacks," exploit modified inputs to cause unexpected behaviours in AIs, such as making a self-driving car misinterpret traffic signs.
● Poisoned data can introduce backdoors into AI models, leading to unintended behaviours, which is concerning due to the lack of control engineers have over their data sources.

Read also on Hello Future

AI therapy: marketing hype and the hidden risks for users

Discover

A lexicon of artificial intelligence: understanding different AIs and their uses

Discover
A presenter is showing graphs on a screen while colleagues listen attentively.

Marketing: AI to supercharge micro-segmentation

Discover

Deepfakes: detection methods struggle to make limited progress

Discover

Generative AI: a growing threat to information systems

Discover

AI agents could further automate certain jobs

Discover