Connect with us


AI data poisoning- A rising concern

Cyber attackers are amping up their attacks through AI tools. In Synopsys’ latest Ponemon Software Supply Chain Security Risk report, 52% of respondents say their development teams leverage AI tools to generate code, 50 percent use OpenAI Codes, and 45 percent use ChatGPT. These numbers are substantial and raise the concern of AI data poisoning.

AI data poisoning is an attack that allows an unauthorized user to train the AI bot/ system. An attacker could teach the AI false information, which can spread misinformation, introduce biases and malware, increase inaccuracies, even denial of service, and create a backdoor!

For the complete report,

CT Bureau

Click to comment

You must be logged in to post a comment Login

Leave a Reply

Copyright © 2024 Communications Today

error: Content is protected !!