The use of transformer-based models is growing rapidly throughout society. With this growth,
it is important to understand how they work, and in particular, how the attention mechanisms …

The objective of digital forgetting is, given a model with undesirable knowledge or behavior,
obtain a new model where the detected issues are no longer present. The motivations for …

Current large language models have dangerous capabilities, which are likely to become
more problematic in the future. Activation steering techniques can be used to reduce risks …

Large language models (LLMs) are vulnerable to adversarial attacks that bypass safety
measures and induce the model to generate harmful content. Securing open-access LLMs …