Trustworthy machine learning addresses methods for training and deploying models that are secure, privacy-preserving, and robust to manipulation. Work in this area develops federated and decentralized learning schemes, cryptographic and homomorphic encryption frameworks, and privacy-preserving compression to protect data and models. It also studies adversarial example generation and defenses, certified unlearning, bias and spurious correlation mitigation, and the use of synthetic and filtered data. Applications span fraud and cyberattack detection, fake news and deception detection, and secure automation systems.
Hi Tech & Innovation
What is it that makes a super recognizer—someone with extraordinary face recognition abilities—better at remembering faces than the rest of us?
Nov 5, 2025
0
38
Security
When you make a voice call through Zoom, FaceTime or WhatsApp, you're not just sharing what you say. You're revealing your age, gender, emotional state, social background and personality—a biometric fingerprint just as unique ...
Oct 28, 2025
0
55
Machine learning & AI
Like humans, artificial intelligence learns by trial and error, but traditionally, it requires humans to set the ball rolling by designing the algorithms and rules that govern the learning process. However, as AI technology ...
Computer Sciences
A new "blueprint" for building AI that highlights how the technology can learn from different kinds of data—beyond vision and language—to make it more deployable in the real world, has been developed by researchers at the ...
Oct 21, 2025
0
28
Security
A research team has developed a new one-shot federated learning artificial intelligence (AI) technique that enables efficient training of large-scale models without sharing personal information. This research outcome is extremely ...
Oct 21, 2025
0
32
Security
Poisoning is a term most often associated with the human body and natural environments.
Oct 20, 2025
0
39
Business
As local governments adopt new technologies that automate many aspects of city services, there is an increased likelihood of tension between the ethics and expectations of citizens and the behavior of these "smart city" tools. ...
Oct 20, 2025
0
27
Security
Federated learning was devised to solve the problem of difficulty in aggregating personal data, such as patient medical records or financial data, in one place. However, during the process where each institution optimizes ...
Oct 15, 2025
0
32
Telecom
SUTD researchers test a privacy-preserving approach that blends federated learning with cloud coordination for smart grids in future 6G environments.
Oct 15, 2025
0
41
Machine learning & AI
Just as human eyes tend to focus on pictures before reading accompanying text, multimodal artificial intelligence (AI)—which processes multiple types of sensory data at once—also tends to depend more heavily on certain types ...
Oct 14, 2025
0
30
