Kinaitics on Difesa online!
Featured on Difesa Online, KINAITICS showcases its collaborative approach involving European partners and cutting-edge solutions to create robust, resilient, and trustworthy AI-powered systems.
Newsletter – Issue 1
Read about the last project updates in our first newsletter
Kinaitics on Ofcs!
Kinaitics has been recognized by OFCS for its innovative efforts in combating prompt injection attacks, a critical threat to the security of generative language models.
Kinaitics: Cybersecurity, information assurance and business continuity
During the Hospitals on FHIR User Days event in Brussels last week, KINAITICS partners discussed how hospitals can benefit from the adoption of the KINAITICS tools.
Kinaitics on Red Hot Cyber!
The article introduces OWASP’s LLM Top Ten, a new framework for addressing the main security risks specific to large language models (LLMs). It highlights vulnerabilities like prompt injection and data leakage, aiming to guide safer AI development. The piece also touches on the European Kinaitics project, which exemplifies the EU’s commitment to secure AI advancements through dedicated research funding.
APWG.EU Tech Summit 2024
The APWG.EU Tech Summit 2024 in Málaga gathers global experts to tackle challenges in cybercrime defense. Davide Ariu from Pluribus One presented Kinaitics, an innovative project for infrastructure protection and combating cybercrime.
Introducing NeuralSentinel: A Tool for Safeguarding Neural Network Reliability and Trustworthiness
NeuralSentinel—a tool developed by the KINAITICS project, designed to enhance the reliability and trustworthiness of neural networks in critical sectors like healthcare, energy, and cybersecurity.
Gain Insights into the Latest Cybersecurity Trends from Horizon Europe Funded Projects
In recent years, the significance of cybersecurity has grown exponentially in an increasingly digital world. This white paper represents a collaborative effort to consolidate insights from eight distinct European projects, all funded to address the evolving cybersecurity landscape.
How to Train Your Antivirus: RL-based Hardening through the Problem Space
Ilias Tsingenopoulos successfully presented his paper, “How to Train Your Antivirus: RL-based Hardening through the Problem Space,” at the 27th International Symposium on Research in Attacks, Intrusions and Defenses (RAID 2024). The prestigious event took place from September 30 to October 2, 2024, at the historic Palazzo della Salute in Padua, Italy.
KU Leuven organized the 3rd Summer School on Security and Privacy in the Age of AI (10-13 September 2024, Leuven, Belgium)
KU Leuven recently hosted a highly successful Summer School on “Security and Privacy in the Age of AI,” drawing 59 researchers from around the world. The event provided a collaborative platform for exploring critical issues at the intersection of Artificial Intelligence, Machine Learning, and Security & Privacy.