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.
Security
Researchers at the University of Tokyo developed a framework to enable decentralized artificial intelligence-based building automation with a focus on privacy. The system enables AI-powered devices like cameras and interfaces ...
May 5, 2025
0
23
Engineering
In industry, the detection of anomalies such as scratches, dents, and discolorations is crucial to ensure product quality and safety. However, conventional methods rely on heavy computational processing and image enhancement ...
May 1, 2025
0
28
Security
An unrelenting, ravenous appetite for more and more data may be artificial intelligence's fatal flaw; or at least the fastest way for "poison" to seep in.
Apr 24, 2025
2
57
Computer Sciences
It's obvious when a dog has been poorly trained. It doesn't respond properly to commands. It pushes boundaries and behaves unpredictably. The same is true with a poorly trained artificial intelligence (AI) model. Only with ...
Apr 24, 2025
0
56
Computer Sciences
ChatGPT and alike often amaze us with the accuracy of their answers, but unfortunately, they also repeatedly give us cause for doubt. The main issue with powerful AI response engines (artificial intelligence) is that they ...
Apr 24, 2025
0
108
Machine learning & AI
MIT researchers have created a periodic table that shows how more than 20 classical machine-learning algorithms are connected. The new framework sheds light on how scientists could fuse strategies from different methods to ...
Apr 23, 2025
0
373
Software
Sound is a powerful source of information. By training algorithms to identify distinct sound signatures, sound can reveal what a person is doing, whether it's cooking, vacuuming or washing the dishes. And while it's valuable ...
Apr 21, 2025
0
74
Computer Sciences
AI models often rely on "spurious correlations," making decisions based on unimportant and potentially misleading information. Researchers have now discovered these learned spurious correlations can be traced to a very small ...
Apr 18, 2025
1
82
Security
As Internet of Things (IoT) devices proliferate in sectors like smart cities, health care, and industrial systems, they have become prime targets for cyberattacks such as Distributed Denial of Service (DDoS), ransomware, ...
Apr 16, 2025
0
41
Consumer & Gadgets
It seems that no matter the topic of conversation, online opinion around it will be split into two seemingly irreconcilable camps.
Apr 15, 2025
0
36
