New Method Efficiently Safeguards Sensitive AI Training Data
Adam Zewe | MIT News
The approach maintains an AI model’s accuracy while ensuring attackers can’t extract secret information.
Security Scheme Could Protect Sensitive Data during Cloud Computation
Adam Zewe | MIT News
MIT researchers crafted a new approach that could allow anyone to run operations on encrypted data without decrypting it first.
To Keep Hardware Safe, Cut Out the Code’s Clues
Alex Shipps | MIT CSAIL
New “Oreo” method from MIT CSAIL researchers removes footprints that reveal where code is stored before a hacker can see them.
Towards Secure Machine Learning Acceleration: Threats and Defenses Across Algorithms, Architecture, and Circuits
Thursday, December 19, 2024
Hybrid
Zoom & MIT Campus
New Security Protocol Shields Data From Attackers During Cloud-based Computation
Adam Zewe | MIT News
The technique leverages quantum properties of light to guarantee security while preserving the accuracy of a deep-learning model.
An integrated MEMS sensing and computing unit: Can a sensor think?
Wednesday, September 11, 2024
Hybrid
Zoom & MIT Campus
This Tiny Chip Can Safeguard User Data while Enabling Efficient Computing on a Smartphone
Adam Zewe | MIT News
Researchers have developed a security solution for power-hungry AI models that offers protection against two common attacks.
Learning on the Edge
Adam Zewe | MIT News Office
A new technique enables AI models to continually learn from new data on intelligent edge devices like smartphones and sensors, reducing energy costs and privacy risks.
Stronger Security for Smart Devices
Adam Zewe | MIT News Office
MIT Researchers demonstrate two security methods that efficiently protect analog-to-digital converters from powerful attacks that aim to steal user data.
Toward a Stronger Defense of Personal Data
Adam Zewe | MIT News Office
MIT Engineers have built a lower-energy chip that can prevent hackers from extracting hidden information from a smart device.