Trusted AI Blog

• LLM Security

This week in AI security: prompt injection, prompt extraction, phishing and model poisoning, plus thousands of ChatGPT jailbreaks offered for sale.

• LLM Security

Here's the top LLM security publications collected in one place for you.

• LLM Security

The adoption of AI in enterprises introduces significant risks that span technical, reputational, regulatory, and operational dimensions.

This week in AI security: NIST's taxonomy of adversarial machine learning attacks, Amazon listings named by a refusal message, and leaked Microsoft AI demos.

• GenAI Security

In a significant development within Israel's burgeoning Generative AI sector, Adversa AI has been included in the latest Israeli Generative AI Market Map.

Consider this scenario: You're preparing a presentation and require an image of a balloon.

This week in AI security: the CSA press release, a study showing large language models deceive users under pressure, and the EU's landmark AI rules.

• LLM Security
• Adversarial ML

Researchers map the vulnerabilities and strengths of AI applications, from classic computer vision to the latest large language and vision-language models.

• LLM Security

This week in AI security: the pressing safety and security concerns raised by the rapid advance of large language models like ChatGPT.

• LLM Security

Hacking LLM? What can be easier? Read it in our monthly LLM Security digest

The rise of customizable AI chatbots, like OpenAI's GPTs, has introduced a new era of convenience in creating personalized AI tools.

Recent developments in artificial intelligence (AI) have raised significant security concerns.