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.
Engineering
In an unfolding disaster situation, quick decisions need to be made on how to respond and where to direct resources, to preserve life and aid recovery efforts. With the rapid development of AI, unmanned aerial vehicles (UAVs) ...
Sep 22, 2025
0
11
Security
A recent study suggests that cyberattacks on future, AI-guided spacecraft could be thwarted by unpicking what the AI has been "thinking."
Sep 18, 2025
0
0
Consumer & Gadgets
Artificial intelligence may well save us time by finding information faster, but it is not always a reliable researcher. It frequently makes unsupported claims that are not backed up by reliable sources. A study by Pranav ...
Computer Sciences
To train artificial intelligence (AI) models, researchers need good data and lots of it. However, most real-world data has already been used, leading scientists to generate synthetic data. While the generated data helps solve ...
Sep 15, 2025
0
23
Business
The rise of e-commerce has brought unprecedented convenience to consumers, but it has also created fertile ground for deceptive practices in online marketplaces. A growing body of research is now focusing on the detection ...
Sep 15, 2025
0
0
Security
As generative AI models move from massive cloud servers to phones and cars, they're stripped down to save power. But what gets trimmed can include the technology that stops them from spewing hate speech or offering roadmaps ...
Sep 5, 2025
0
31
Security
A team of computer scientists at the University of Toronto recently discovered that a certain type of hardware attack is effective against graphics processing units (GPUs), the core computing engines that power today's artificial ...
Sep 4, 2025
0
15
Machine learning & AI
Synthetic data are artificially generated by algorithms to mimic the statistical properties of actual data, without containing any information from real-world sources. While concrete numbers are hard to pin down, some estimates ...
Sep 3, 2025
0
2
Computer Sciences
A team of computer scientists at UC Riverside has developed a method to erase private and copyrighted data from artificial intelligence models—without needing access to the original training data.
Aug 29, 2025
0
28
Engineering
Recently, defect detection systems using artificial intelligence (AI) sensor data have been installed in smart factory manufacturing sites. However, when the manufacturing process changes due to machine replacement or variations ...
Aug 26, 2025
0
0
