Abstract
Safety Neurons in Large Language Models
Large language models (LLMs) achieve state-of-the-art performance across a wide range of tasks, but their widespread deployment raises urgent concerns around security, privacy, and misuse. Building on recent...
Abstract
Cyber space is expanding fast with the introduction of new Internet of Things (IoT) and CPS devices. Wearables, smart watches, smart glasses, fitness trackers, medical devices, Internet-connected house appliances and vehicles have grown exponentially in a short...
Abstract: The talk will be a summary of my research activities from the practical ones, in the fields of cyber-security and compilers testing, to the one of a more theoretical nature in distributed computing.
...What would the world be like if software had no bugs? Software systems would be impenetrable and our data shielded from prying eyes? Not quite. In this talk, I will present evidence that reliable attacks targeting even "perfect" software are a realistic threat. Such attacks exploit properties of...
