Microsoft has revealed specifics about a new side-channel attack aimed at remote language models. This attack could allow a passive adversary with the ability to monitor network traffic to extract information about conversation topics within the model, even when encryption is in place, under certain conditions.
The company indicated that this leakage of data shared between individuals and streaming-mode language models could significantly threaten the privacy of user and enterprise communications. The assault has received the codename Whisper Leak.
Cyber attackers who can monitor encrypted traffic (such as a nation-state actor at the internet service provider layer, an individual on the local network, or someone using the same Wi-Fi connection) may leverage this cyber attack to deduce whether the user’s prompt pertains to a certain topic, according to security researchers Jonathan Bar Or and Geoff McDonald and the Microsoft Defender Security Research Team read more about Microsoft Uncovers ‘Whisper Leak’ Attack That Identifies AI Chat Topics in Encrypted Traffic.
Get up to date on the latest cybersecurity news and enhance your knowledge of cybersecurity with our thorough coverage of the dangers, breaches, and solutions.