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
64
Computer Sciences
The work of University of Tartu intersectoral doctoral researcher Eduardo Brito could reshape how we verify truth in the digital world. His research on a decentralized Proof-of-Location system, recently published in Scientific ...
Aug 11, 2025
0
52
Security
Visual artists want to protect their work from non-consensual use by generative AI tools such as ChatGPT. But most of them do not have the technical know-how or control over the tools needed to do so.
Aug 5, 2025
0
52
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
62
Security
Most of the companies behind large language models like ChatGPT claim to have guardrails in place for understandable reasons. They wouldn't want their models to, hypothetically, offer instructions to users on how to hurt ...
Jul 31, 2025
0
60
Security
Fact-checkers may have a new tool in the fight against misinformation.
Jul 30, 2025
0
82
Security
What we see on our mobile phone screens is not always what we are actually operating. This has been demonstrated by a research team at TU Wien (Vienna, Austria), consisting of Philipp Beer, Sebastian Roth, Marco Squarcina, ...
Jul 17, 2025
0
477
Security
Researchers have demonstrated a new way of attacking artificial intelligence computer vision systems, allowing them to control what the AI "sees." The research shows that the new technique, called RisingAttacK, is effective ...
Jul 1, 2025
0
160
Hardware
Seoul National University College of Engineering announced that a research team has developed a new hardware security technology based on commercially available 3D NAND flash memory (V-NAND flash memory).
Jun 30, 2025
0
63
