IntelVerse

In this episode of the O’Reilly Data Show, I spoke with Danny Bickson, co-founder and VP at Dato, and the principal organizer of the Data Science Summit (full disclosure: I’m a member of the conference organizing committee). Among machine learning students and practitioners, recommender systems have become somewhat of a canonical use case and application. One of the early and popular building blocks was GraphLab’s collaborative filtering toolkit, a library originally written and maintained by Bickson. He has continued to keep tabs on the latest developments in recommenders and continues to help organize workshops on related topics throughout the world.

Building and Deploying Large-Scale Machine Learning Applications

When Google’s DeepMind won against one of the best modern Go champions, is used multiple AI approaches and exposed gaps in some individual strategies. This even has shed more light on AI, but also on the utility in combining approaches to AI for individual problems. Data security is one of these problem areas&nbsp;where multiple AI approaches is being used to make our information safer. Dr. Sal Stolfo has been a professor at Columbia in Computer Science since 1972 and is now also the CEO of Allure Security, with a focus on engineering network intrusion detection solutions using AI&nbsp;applications. In this episode, Stolfo talks about the various styles of AI and statical methods that have been and are being used&nbsp;to detect malicious activity, as well as how he believes the future of security is going to have to adapt as increasing amounts of data become available.

Network Intrusion Detection Using Machine Learning

In this episode of the Data Show, I spoke with Parvez Ahammad, who leads the data science and machine learning efforts at Instart Logic. He has applied machine learning in a variety of domains, most recently to computational neuroscience and security. Along the way, he has assembled and managed teams of data scientists and has had to grapple with issues like explainability and interpretability, ethics, insufficient amount of labeled data, and adversaries who target machine learning models. As more companies deploy machine learning models into products, it’s important to remember there are many other factors that come into play aside from raw performance metrics.

Building Machine Learning Solutions That Can Withstand Adversarial Attacks

In this episode of the Data Show, I spoke with Andrew Burt, chief privacy officer and legal engineer at Immuta, a company building data management tools tuned for data science. Burt and cybersecurity pioneer Daniel Geer recently released a must-read white paper (“Flat Light”) that provides a great framework for how to think about information security in the age of big data and AI. They list important changes to the information landscape and offer suggestions on how to alleviate some of the new risks introduced by the rise of machine learning and AI.

We discussed their new white paper, cybersecurity (Burt was previously a special advisor at the FBI), and an exciting new Strata Data tutorial that Burt will be co-teaching in March.

How Machine Learning Impacts Information Security

Three generals are voting on whether to attack or retreat from their siege of a castle. One of the generals is corrupt and two of them are not. What happens when the corrupted general sends different answers to the other two generals?

A Byzantine fault is "a condition of a computer system, particularly distributed computing systems, where components may fail and there is imperfect information on whether a component has failed. The term takes its name from an allegory, the "Byzantine Generals' Problem", developed to describe this condition, where actors must agree on a concerted strategy to avoid catastrophic system failure, but some of the actors are unreliable."

The Byzantine Generals' Problem and associated issues in maintaining reliable distributed computing networks is illuminating for both AI alignment and modern networks we interact with like Youtube, Facebook, or Google. By exploring this space, we are shown the limits of reliable distributed computing, the safety concerns and threats in this space, and the tradeoffs we will have to make for varying degrees of efficiency or safety.

The Byzantine Generals' Problem, Poisoning, and Distributed Machine Learning with El Mahdi El Mahmdi is the ninth podcast in the AI Alignment Podcast series, hosted by Lucas Perry. El Mahdi pioneered Byzantine resilient machine learning devising a series of provably safe algorithms he recently presented at NeurIPS and ICML. Interested in theoretical biology, his work also includes the analysis of error propagation and networks applied to both neural and biomolecular networks. This particular episode was recorded at the Beneficial AGI 2019 conference in Puerto Rico. We hope that you will join in the conversations by following us or subscribing to our podcasts on Youtube, SoundCloud, iTunes, Google Play, Stitcher, or your preferred podcast site/application. You can find all the AI Alignment Podcasts here.

If you're interested in exploring the interdisciplinary nature of AI alignment, we suggest you take a look here at a preliminary landscape which begins to map this space.

Topics discussed in this episode include:

The Byzantine Generals' Problem
What this has to do with artificial intelligence and machine learning
Everyday situations where this is important
How systems and models are to update in the context of asynchrony
Why it's hard to do Byzantine resilient distributed ML.
Why this is important for long-term AI alignment
An overview of Adversarial Machine Learning and where Byzantine-resilient Machine Learning stands on the map is available in this (9min) video . A specific focus on Byzantine Fault Tolerant Machine Learning is available here (~7min)

In particular, El Mahdi argues in the first interview (and in the podcast) that technical AI safety is not only relevant for long term concerns, but is crucial in current pressing issues such as social media poisoning of public debates and misinformation propagation, both of which fall into Poisoning-resilience. Another example he likes to use is social media addiction, that could be seen as a case of (non) Safely Interruptible learning. This value misalignment is already an issue with the primitive forms of AIs that optimize our world today as they maximize our watch-time all over the internet.

The latter (Safe Interruptibility) is another technical AI safety question El Mahdi works on, in the context of Reinforcement Learning. This line of research was initially dismissed as "science fiction", in this interview (5min), El Mahdi explains why it is a realistic question that arises naturally in reinforcement learning

El Mahdi's work on Byzantine-resilient Machine Learning and other relevant topics is available on
his Google scholar profile.

The Byzantine Generals' Problem, Poisoning, and Distributed Machine Learning with El Mahdi El Mhamdi

Emerj.com is where business leaders turn to understand how AI is impacting their business and industry - and what to do about it.

Our objective, jargon-free research and industry overviews are designed to give executives and decision-makers exactly what they need for competitive insight, informed AI technology procurement and strategic planning around AI.

AI disruption will open up new vistas for opportunity, creating new business paradigms and making others extinct. 

Emerj market research helps leaders survive and thrive in an era of AI disruption.

www.emerj.com

Network Intrusion Detection Using Machine Learning

The AI in Business Podcast