Jailbreak LLMs – Games and resources for learning about AI Red Teams
Privacy tests help you protect people. If you have data about people, you are responsible for reducing potential harm to them. The most important reason to run a privacy test is to help keep people safe. It’s easy to get lost in the details of privacy compliance and legal wording when building a privacy…
Can a machine test for responsible and trustworthy AI
Can you imagine building software without testing it? It’s hard to believe there was a time when many software teams didn’t write tests, and just handed the testing off to a separate Quality Assurance team. I remember those days; I was writing web applications in Perl when I first discovered unit tests. I was…
Are good intentions enough to justify de-anonymizing a dataset? Imagine you are a privacy engineer faced with this conversation: Manager: “Hey, we have a bunch of data on how people do X, and we are going to share it with Y? We removed all the identifiers, so it should be good enough, right” Privacy Engineer:…
Wouldn’t it be nice if your data protection program was resilient to changing privacy requirements? Imagine if you could exceed today’s regulatory compliance requirements and prepare for the changing landscape of tomorrow. I suggest three options to enable your privacy program to be proactive (instead of reactive) to new regulations. Additionally, these will make…
Some large companies are building privacy red teams to test their privacy controls. Other companies are exploring adding privacy capabilities to their security red team efforts. This introduction is for people who want to learn how a privacy red team is different from a security red team. What is a red team? A security red…
Great privacy foundations may not be enough to ensure lasting privacy protections