So, you wanna do at-home AI? Yes, you do!

There's a bunch of great reasons to run your own AI including having more control over your data and models, learning more about how deep learning works, testing out new ideas without having to pay extra cloud or subscription costs and …

In the last article in the series on addressing the problems of memorization in deep learning and AI, you learned about differential privacy and how to apply it to deep learning/AI systems. In this article, you'll explore what can go wrong when using differential privacy training in deep learning …

Differential privacy influenced both privacy attacks and defenses you've investigated in this series on AI/ML memorization. You might be wondering: what exactly is differential privacy when it's applied to deep learning? And can it address the problem of memorization?

Are you a visual learner? There's a YouTube video on …

In the past articles, you've been exploring the field of machine unlearning, investigating if you can surgically remove memorized or learned data from models without retraining them from scratch or from an earlier checkpoint.

Unlearning is one proposed solution to the AI/ML memorization problem explored in this multi-article series …

Building on our understanding of machine unlearning and its varied definitions, in this article you'll learn common approaches to implementing unlearning. To effectively use these approaches, you'll first want to define what unlearning definition and measurement fits your needs.

In current unlearning research, there are three main categories of unlearning …

Machine unlearning sounds pretty cool. It is the idea that you can remove information from a trained model at will. If this was possible, you'd be able to edit out things you don't want the model to know, from criminal behavior, racialized slurs to private information. It would solve many …

It seems like every week my LinkedIn feed is filled with new just released AI risk taxonomies, threat models or AI governance handbooks. Usually these taxonomies come from governance consultants or standards authorities and are a great reference for understanding the wide variety of risks AI systems¹ bring with …

You've probably at some point heard the term "guardrails" when talking about security or safety in AI systems like LLMs or multi-modal models (i.e. models that include and produce multiple modalities, like speech and image, videos, image and text).

Are you a visual learner? There's a YouTube video for …

One common way to control memorization in today's deep learning systems is to fix the problem by building software around it. This software can also be used to deal with other undesired behavior, like producing hate speech or mentioning criminal activities.

Are you a visual learner? There's a YouTube video …

In this article series, you've been able to investigate memorization in AI/deep learning systems -- often via interesting attack vectors. In security modeling, it's useful to explicitly define the threats you are defending against, so you can both discuss and address them and compare potential interventions.

Prefer to learn by …