Upgrade 2024: Let's Upgrade Reality

April 11, 2024 // Upgrade 2024

Safeguarding the Human-AI Interface: Building Trust and Security in Conversational Systems​

Moshe Karako

Summary

Safeguarding the Human-AI Interface: Building Trust and Security in Conversational Systems​

Chatbots and virtual assistants are becoming ubiquitous, but their security remains an afterthought. This exposes users to privacy breaches, manipulation, and other harms from adversarial attacks. Users want to trust that artificial intelligence (AI) systems have their best interests in mind. Building the needed trust requires making conversational interfaces more safe, transparent, and ethical. This session explores emerging risks in human-AI communication and strategies to mitigate them. Technical approaches like differential privacy, federated learning, and formal verification that protect user data and make systems more robust will be discussed. Organizational best practices around transparency, accountability, and ethics review boards are also covered.

Our Research

News & Media

Events

Your Privacy

When you visit any website, it may store or retrieve information on your browser, mostly in the form of cookies. This information might be about you, your preferences or your device and is mostly used to make the site work as you expect it to. The information does not usually directly identify you, but it can give you a more personalized web experience. Because we respect your right to privacy, you can choose not to allow some types of cookies. Click on the different category headings to find out more and change our default settings. However, blocking some types of cookies may impact your experience of the site and the services we are able to offer.