Speaker discusses risks of trusting AI with personal data
From Masters of Scale
AIcybersecuritydata privacytechnologyLLM systems
Transcript
And so it acts on that text and can do, you know, it can be made to do or it can accidentally in terms of, you know, reading text and sort of interpreting it statistically to do one or another things to, you know, exfiltrate data, to share your home address, to publish your letters with your boyfriend, to exfiltrate your signal messages, to do, you know, whatever it is that that text says. Now, probably prompt injection is not a solved problem. When Anthropic tested an agent with Chrome, the browser, in 11% of cases, even with the safeguards that one of the richest, most well resourced, Frontier Labs put in place, 11% of cases, prompt injection still worked on this agent. You have the UK's National Cybersecurity Agency saying prompt injection may never be solved for LLM based agent systems. So this is not like a minor bug, we just kind of need to figure out how to patch. This is a fundamental issue with the way that LLM systems and agents that rely on them work. And when we are telling agents, when we are telling people to install these agents in the name of convenience, in the name of like, plan my party for me agents, we are asking them to install a system that has access to their most intimate data, credit card banking, your love notes to your lover, whatever it is, and that is then given permission to act on that data, to combine it all in a big pool of data, to act on your behalf, to impersonate you in your browser, to impersonate you when it's calling customer support, to impersonate you with your bank, and is subject to these kind of prompt injection attacks that again are not remediable, that the front ends and are malicious, could be malicious. We have a prompt injection that researchers showed was kind of able to through a calendar setting, putting malicious text in a calendar setting, sort of a calendar invite, and then asking the agent, sort of summarize my calendar for me. It summarizes everything, including this text that prompted the agent to turn on a boiler, open the shutters and otherwise use someone's smart home devices through a calendar summary. Now that was an.