Security
Artificial intelligence models that are trained to behave badly on a narrow task may generalize this behavior across unrelated tasks, such as offering malicious advice, suggests a new study. The research probes the mechanisms ...
Jan 15, 2026
0
56
Security
You can probably quickly tell from a friend's tone of voice whether they're feeling happy or sad, energetic or exhausted. Computers can already do a similar analysis, and soon they'll be able to extract a lot more information. ...
Jan 14, 2026
0
36
Computer Sciences
The data inputs that enable modern search and recommendation systems were thought to be secure, but an algorithm developed by Cornell Tech researchers successfully teased out names, medical diagnoses and financial information ...
Jan 13, 2026
1
50
Security
What is patient privacy for? The Hippocratic Oath, thought to be one of the earliest and most widely known medical ethics texts in the world, reads: "Whatever I see or hear in the lives of my patients, whether in connection ...
Jan 6, 2026
0
24
Security
Researchers have developed the first scientifically validated "personality test" framework for popular AI chatbots, and have shown that chatbots not only mimic human personality traits, but their "personality" can be reliably ...
Dec 18, 2025
0
61
Telecom
A research team at the University of Ottawa has developed an advanced artificial intelligence system designed to autonomously defend wireless networks from jamming attacks, operating much like a digital immune system. This ...
Dec 17, 2025
0
39
Internet
A new site that tracks the daily fluctuating costs behind building a bot army on over 500 social media and commercial platforms—from TikTok to Amazon and Spotify—in every nation on the planet is launched today by the University ...
Dec 11, 2025
0
59
Security
Southwest Research Institute identified a security vulnerability in a standard protocol governing communications between electric vehicles (EV) and EV charging equipment. The research prompted the Cybersecurity & Infrastructure ...
Nov 18, 2025
0
46
Security
Security researchers have developed the first functional defense mechanism capable of protecting against "cryptanalytic" attacks used to "steal" the model parameters that define how an AI system works.
Nov 17, 2025
0
36
Security
Five minutes of training can significantly improve people's ability to identify fake faces created by artificial intelligence, new research shows.
Nov 12, 2025
0
87
