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.
Software
AI users and developers can now measure the amount of electricity various AI models consume to complete tasks with an open-source software and online leaderboard developed at the University of Michigan. Companies can download ...
13 hours ago
0
5
Security
Artificial intelligence (AI) systems are now widely used by millions of people worldwide, as tools to source information or tackle specific tasks more rapidly and efficiently. Today, some of the most used are large language ...
Security
A newly discovered vulnerability could allow cybercriminals to silently hijack the artificial intelligence (AI) systems in self-driving cars, raising concerns about the security of autonomous systems increasingly used on ...
Feb 20, 2026
0
13
Machine learning & AI
AI systems already decide how ambulances are routed, how supply chains operate and how autonomous drones plan their missions. Yet when those systems make a risky or counterintuitive choice, humans are often expected to accept ...
Feb 20, 2026
0
0
Machine learning & AI
Achieving high reliability in AI systems—such as autonomous vehicles that stay on course even in snowstorms or medical AI that can diagnose cancer from low-resolution images—depends heavily on model robustness. While ...
Jan 29, 2026
0
0
Security
Deep neural networks (DNNs) have become a cornerstone of modern AI technology, driving a thriving field of research in image-related tasks. These systems have found applications in medical diagnosis, automated data processing, ...
Jan 23, 2026
0
20
Security
A new forensic framework designed specifically for the Internet of Things (IoT) is discussed in the International Journal of Electronic Security and Digital Forensics. This deep learning-driven system offers benefits over ...
Jan 15, 2026
0
0
Business
Defense Secretary Pete Hegseth said Monday that Elon Musk's artificial intelligence chatbot Grok will join Google's generative AI engine in operating inside the Pentagon network, as part of a broader push to feed as much ...
Jan 13, 2026
0
0
Machine learning & AI
Training artificial intelligence models is costly. Researchers estimate that training costs for the largest frontier models will exceed $1 billion by 2027. Costs are incurred through hardware, including large data centers, ...
Jan 12, 2026
0
0
Computer Sciences
Artificial intelligence (AI), particularly deep learning models, are often considered black boxes because their decision-making processes remain difficult to interpret. These models can accurately identify objects—such ...
Jan 8, 2026
0
0
