TechXplore-Security

Oak Ridge National Laboratory’s Center for Artificial Intelligence Security Research (CAISER) is shining a light on AI vulnerabilities. While AI models offer tremendous economic, humanitarian and national security potential, they are also increasingly susceptible to […]

Anyone who has recently traveled to the United States will be familiar with biometric checks—facial and fingerprint scans—used at the border. It is the same technology platform that is used in airports elsewhere in the […]

Researchers from the University of Huddersfield have developed a hybrid AI tool to detect patterns of psychological abuse, including coercive control, in a bid to transform digital forensic investigations and mental health research.This innovation was […]

Artificial intelligence is making cyberattacks increasingly sophisticated and costlier for businesses, reinsurer Munich Re said Wednesday, warning of methods ranging from highly personalized phishing emails to computer-generated, convincing fake identities.This post was originally published on […]

In a new article, researchers introduce the capabilities approach–contextual integrity (CA-CI), a framework that addresses privacy and dignity risks posed by modern artificial intelligence (AI) systems, especially foundation models whose capabilities evolve across contexts and […]

Researchers have discovered that some of the elements of AI neural networks that contribute to data-privacy vulnerabilities are also key to the performance of those models. The researchers used this new information to develop a […]

AI-generated images and videos pose a threat to democratic processes and undermine trust within society. Researchers at ETH Zurich have now developed chip technology that enables verification of the authenticity of sensor data including images […]

On a quiet suburban street, a modern Australian home wakes before its owners do.This post was originally published on this site

Researchers have identified key components in large language models (LLMs) that play a critical role in ensuring these AI systems provide safe responses to user queries. The researchers used these insights to develop and demonstrate […]

From password resets and software updates to phishing alerts and cybersecurity trainings, today’s workplace is filled with constant reminders about digital security. But new research led by the University at Albany’s Massry School of Business […]