Trusted AI Blog

This week in AI security: a warning that AI becomes uncontrollable within two years, how CISOs can balance AI risk and benefit, and insecure GitHub projects.

• LLM Security
• Adversarial ML

This digest delves into four riveting research papers that explore adversarial attacks on various machine learning models.

The CEO and founder of Adversa AI Alex Polyakov has been invited to participate in Cyber Week at Tel Aviv University.

• LLM Security

This week in AI security: ChatGPT talked into generating Windows keys, the OWASP Top 10 for LLMs, and compromised ChatGPT accounts for sale on the dark web.

This week in AI security: the World Economic Forum's step toward safeguarding AI systems, plus NVIDIA's updates and strategies for securing AI.

In the ever-expanding field of artificial intelligence (AI), ensuring the security and safety of AI systems has emerged as a critical concern.

The recent controversy surrounding an alleged simulated test conducted by the U.S.

• Adversarial ML

New Arxiv research on neurosymbolic AI, vision-language models, prompt injection, and drone behavior manipulation, with what each paper means for defenders.

• LLM Security

With this monthly digest, feel free to discover the power of ChatGPT!

This week in AI security: the security challenges facing AI, and the defense strategies proposed against them.

This week in AI security: the risks of prompt injection exploits, newly revealed, and the rest of the week's news worth reading.

• LLM Security

This week in AI security: managing the risks that come with ChatGPT integrations, and the rest of the week's news worth reading.