Birgit Hofer and Thomas Hirsch from TU Graz have developed a new approach to speed up software bug fixes. By identifying bottlenecks in fault localization, they created a scalable solution using NLP and metrics to analyze code for faults.

A bug hunter discovered a bypass in Meta's Prompt-Guard-86M model by inserting character-wise spaces between English alphabet characters, rendering the classifier ineffective in detecting harmful content.

A team of researchers from the University of California San Diego has developed a firmware update to hide a smartphone's unique Bluetooth fingerprint, which can be used to track the user.

Google has developed a framework known as Project Naptime, which utilizes a large language model (LLM) for vulnerability research. The framework allows an AI agent to simulate the actions and workflow of a human security researcher.

Google's Project Zero team of zero-day hunters believes that artificial intelligence (AI) can enhance automated threat identification and analysis by detecting vulnerabilities that are often missed by current tools.

Researchers from the Rochester Institute of Technology (RIT) have developed CTIBench, a benchmark designed to evaluate the performance of large language models (LLMs) in cyber threat intelligence (CTI) applications.

By using Open AI's ChatGPT chatbot, the researchers were able to convince cybercriminals to share sensitive information, such as bank account numbers from over 600 financial institutions across 73 countries.

A U.K. government official on Tuesday touted the potential of a processor designed to prevent memory-based cyberattacks even as he acknowledged commercial hurdles to its widespread adoption.

AI jailbreaks can lead to various risks and harms, including unauthorized data access, sensitive data exfiltration, generating ransomware, subversion of decision-making systems, and IP infringement.

In a May 2024 update published ahead of the AI Seoul Summit 2024, co-hosted by the UK and South Korea on 21-22 May, the UK AISI shared the results of a series of tests performed on five leading AI chatbots.