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.
Computer Sciences
AI image generation—which relies on neural networks to create new images from a variety of inputs, including text prompts—is projected to become a billion-dollar industry by the end of this decade. Even with today's technology, ...
Jul 22, 2025
0
35
Computer Sciences
What began as a Ph.D. project has grown into a website with 120,000 unique visitors each year. With the platform OpenML, researcher Jan van Rijn is contributing to open science, aiming to make machine learning more transparent, ...
Jul 21, 2025
0
32
Machine learning & AI
Artificial intelligence is accelerating at breakneck speed, with larger models dominating the scene—more parameters, more data, more power. But here is the real question: Do we really need bigger to be better? We challenged ...
Consumer & Gadgets
Machine learning is an integral part of high-stakes decision-making in a broad swath of human-computer interactions. You apply for a job. You submit a loan application. Algorithms determine who advances and who is declined.
Jul 17, 2025
0
7
Machine learning & AI
Assessing the progress of new AI language models can be as challenging as training them. Stanford researchers offer a new approach.
Jul 15, 2025
0
20
Hi Tech & Innovation
In a study published in the journal Information Systems Research, Texas Tech University's Shuo Yu and his collaborators developed a generative machine learning model to detect instability before a fall occurs. The hope is ...
Jul 11, 2025
0
0
Computer Sciences
Detecting writing via artificial intelligence is a tricky dance: Doing it right means being effective at identifying it while being careful not to falsely accuse a human of employing it. And few tools strike the right balance.
Jul 10, 2025
0
12
Energy & Green Tech
Artificial intelligence (AI) can be made more sustainable by making practical changes, such as reducing the number of decimal places used in AI models, shortening responses, and using smaller AI models, according to research ...
Jul 9, 2025
0
46
Security
In the heart of Data Center Alley—a patch of suburban Washington where much of the world's internet traffic flows—Visa operates its global fraud command center.
Jul 7, 2025
0
0
Security
Researchers have discovered a modern solution to detect vault applications (apps) on smartphones, which could be a game-changer for law enforcement. The paper is published in the journal Future Internet.
Jun 27, 2025
0
48
