New prompt-based technique to enhance AI security

The diagram of the study’s prompt-based attack approach (PAT). Credit: Frontiers of Computer Science (2023). DOI: 10.1007/s11704-023-2639-2 Researchers have developed a new approach to AI security that employs text prompts to better protect AI systems from cyber threats. This method focuses on the creation of adversarial examples to prevent AI from being misled by inputs […]

How AI tackles complex data sampling

Credit: Pixabay/CC0 Public Domain The world of artificial intelligence (AI) has recently seen significant advancements in generative models, a type of machine-learning algorithm that “learns” patterns from sets of data in order to generate new, similar sets of data. Generative models are often used for things like drawing images and natural language generation—a famous example […]

An eerie ‘digital afterlife’ is no longer science fiction. So how do we navigate the risks?

Credit: Pixabay/CC0 Public Domain Imagine a future where your phone pings with a message that your dead father’s “digital immortal” bot is ready. This promise of chatting with a virtual version of your loved one—perhaps through a virtual reality (VR) headset—is like stepping into a sci-fi movie, both thrilling and a bit eerie. As you […]

330 Weeks of Data Visualizations: My Journey and Key Takeaways | by Yu Dong | Jun, 2024

How constant apply in information visualization enhanced my information science abilities I’ve been making one visualization weekly since I began my full-time information science job in 2018. Now, over 330 weeks later, I contemplate this an achievement I’m really happy with. Throughout espresso chats, individuals typically ask me about it, which impressed me to jot […]

Correcting biases in image generator models

Editing a model based on a source and destination prompt. The edit generalizes to related prompts (green), leaving unrelated ones unaffected (gray). Credit: Hadas Orgad et al Image generator models—systems that produce new images based on textual descriptions—have become a common and well-known phenomenon in the past year. Their continuous improvement, largely relying on developments […]

Meet CARMEN, a robot that helps people with mild cognitive impairment

Ph.D. student Anya Bouzida, one of the paper’s first authors, demonstrates how CARMEN works. Credit: David Baillot/University of California San Diego Meet CARMEN, short for Cognitively Assistive Robot for Motivation and Neurorehabilitation—a small, tabletop robot designed to help people with mild cognitive impairment (MCI) learn skills to improve memory, attention, and executive functioning at home. […]