Trusted AI Blog

This week in AI security: UT Austin and MITRE investing in ethical AI, the UK's proposed AI rulebook, and a whistleblower on a robotaxi launched too early.

This week in AI security: new adversarial mask designs that evade facial recognition, a government defense center for AI research, and the question of AI bias.

Adversarial machine learning and artificial intelligence are a concern in the information security community.

• Adversarial ML

Science-fiction writers are fond of using artificial intelligence (AI) as the antagonist in their stories.

Concerns about the security of AI systems are on the rise

At ML Conference 2022 we walked through threat modeling for machine learning: what to model, where the boundaries sit, and what usually gets missed.

Machine Learning models not as secure and safe as it might seem at first glance

AI Red Teaming - Before using any technology, you must make sure it is safe and secure

The annual machine learning (ML) security evasion competition invites ML practitioners and security researchers to compete against their peers.

• Adversarial ML

Carrying out attacks on machine learning models as part of the study is necessary for further successful work on potential vulnerabilities.

Knowledge about artificial intelligence and its security needs to be constantly improved

• Adversarial ML

Cyber Defense Magazine named Adversa AI winner of its Next Gen Adversarial ML Threat Mitigation award at the 10th Global InfoSec Awards during RSAC 2022.