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
A key objective of behavioral science research is to better understand how people make decisions in situations where outcomes are unknown or uncertain, which entail a certain degree of risk.
Security
A self-driving motor vehicle is cruising along, its numerous sensors and cameras telling it when to brake, change lanes, and make turns. The vehicle approaches a stop sign at a high rate of speed, but instead of stopping, ...
Aug 13, 2025
0
63
Security
Imagine a busy train station. Cameras monitor everything, from how clean the platforms are to whether a docking bay is empty or occupied. These cameras feed into an AI system that helps manage station operations and sends ...
Aug 13, 2025
0
51
Security
Researchers from the University of Oxford, EleutherAI, and the UK AI Security Institute have reported a major advance in safeguarding open-weight language models. By filtering out potentially harmful knowledge during training, ...
Aug 12, 2025
0
63
Security
A new technique developed by Australian researchers could stop unauthorized artificial intelligence (AI) systems learning from photos, artwork and other image-based content.
Aug 12, 2025
0
44
Machine learning & AI
A new approach called open ad-hoc categorization (OAK) helps AI systems dynamically reinterpret the same image differently depending on the categorization context, rather than using fixed visual interpretation. A University ...
Aug 6, 2025
0
42
Computer Sciences
AI is a relatively new tool, and despite its rapid deployment in nearly every aspect of our lives, researchers are still trying to figure out how its "personality traits" arise and how to control them. Large learning models ...
Machine learning & AI
OpenAI on Tuesday released two new artificial intelligence (AI) models that can be downloaded for free and altered by users, to challenge similar offerings by US and Chinese competition.
Aug 5, 2025
0
69
Computer Sciences
When it comes to cybersecurity, humans are often seen as the weakest link, but new research suggests that with a little help, people can do a surprisingly effective job at identifying malware.
Aug 5, 2025
0
59
Security
New vulnerabilities have emerged with the rapid advancement and adoption of multimodal foundational AI models, significantly expanding the potential for cybersecurity attacks. Researchers at Los Alamos National Laboratory ...
Aug 4, 2025
0
61
