Your AI Assistant Has a Big Mouth: A New Side Channel Attack
Side-channel traffic analysis attack that intercepts and reconstructs confidential AI assistant chat conversations across major platforms.
Summary
Privacy in Modern AI Assistants
AI assistants like ChatGPT are changing how we interact with technology. But what if someone could read your confidential chats? Imagine awkwardly asking your AI about a strange rash, or to edit an email, only to have that conversation exposed to someone on the net. In this talk we'll unveil a novel side-channel vulnerability in popular AI assistants and demonstrate how it can be used to read encrypted messages sent from AI Assistants.
Side Channel Traffic Analysis Exploit
Before our disclosure, major players like OpenAI, Microsoft, Cloudflare, Quora, and Notion were at risk. We'll reveal the technical details of this exploit and show real-world examples of intercepted conversations. This talk isn't just about the problem – learn how to identify this vulnerability in other AI assistants as well! We'll dissect network traffic, discuss attack models, and explore the far-reaching consequences of this discovery.
Related talks
Main Stage·50 min
Olivier Bilodeau · Estelle Ruellan
Demonstrates leveraging multimodal LLMs to analyze millions of infostealer infection screenshots and autonomously extract indicators of compromise.
Main Stage·32 min
Alexandre Grattafiori · Ivan Evtimov · Ron Bitton
Methodologies, automated multi-turn adversarial agents, and benchmark tooling used by Meta's AI Red Team to test Llama 3.
Main Stage·26 min
Adam Shostack
Frameworks and threat modeling methodologies adapted to identify and mitigate risks introduced by machine learning and AI systems.