In recent years, medical researchers have devised various new techniques that can help them to organize and analyze large amounts of research data, uncovering links between different variables (e.g., diseases, drugs, proteins, etc.). One of these methods entails...
Security
New ransomware attack based on an evolutional generative adversarial network can evade security measures
In recent years, cyber attackers have become increasingly skilled at circumventing security measures and successfully targeting technology users. Developing effective methods to detect, neutralize or mitigate the impact of these attacks is of utmost importance.
Tackling long-range malware detection tasks using holographic global convolutional networks
Over the past few decades, cyber-attackers have devised increasingly sophisticated malware that can disrupt the functioning of computer systems or grant them access to sensitive data. The development of techniques that can reliably detect the presence of malware and...
A framework to enhance the safety of text-to-image generation networks
The emergence of machine learning algorithms that can generate texts and images following human users' instructions has opened new possibilities for the low-cost creation of specific content. A class of these algorithms that are radically transforming creative...
A camera-based anti-facial recognition technique
Facial recognition systems, computational tools that can recognize individuals in images or video footage, are now widely employed worldwide. Some users and developers, however, have raised privacy-related concerns, as by definition facial recognition techniques rely...
A simple technique to defend ChatGPT against jailbreak attacks
Large language models (LLMs), deep learning-based models trained to generate, summarize, translate and process written texts, have gained significant attention after the release of Open AI's conversational platform ChatGPT. While ChatGPT and similar platforms are now...
Study unveils vulnerabilities of watermarking AI generated content
With the advent of LensaAI, ChatGPT and other highly performing generative machine learning models, the internet is now growing increasingly saturated with texts, images logos and videos created by artificial intelligence (AI). This content, broadly referred to as AI...
A decentralized, blockchain-based messaging network for safer communications
Data and security breaches are becoming increasingly common, highlighting the vulnerabilities of existing messaging and communications platforms. Devising computational tools and systems that better protect sensitive data against malicious attacks is therefore of...
Study highlights the vulnerabilities of metasurface-based wireless communication systems
Metasurfaces, artificially engineered surfaces that can manipulate electromagnetic signals in unique ways, have huge potential for several technological applications, including the implementation of sixth generation (6G) cellular communications. The limitations and...
A CMOS-compatible spintronic compute-in-memory macro to secure AI edge devices
Edge computing applications, which entail the processing and storage of data at the source of its production (i.e., near where it is created), is now being applied to a growing number of technologies. The application of edge computing translates into devices that can...