In May we were invited to present our work to a global audience of Google engineers and scientists working on ML. Security people also participated. The talk was delivered via video and hosted by Google Zurich.
A few hundred people participated live. Unfortunately, though the session was recorded on video, Google has requested that we not post the video. OK Google. You do know what we said about you is what we say to everybody about you. Whatever. LOL.
Here is the talk abstract and a bio for McGraw who did the presentation. If you would like to host a BIML presentation for your organization, get in touch.
10, 23, 81 — Stacking up the LLM Risks: Applied Machine Learning Security
I present the results of an architectural risk analysis (ARA) of large language models (LLMs), guided by an understanding of standard machine learning (ML) risks previously identified by BIML in 2020. After a brief level-set, I cover the top 10 LLM risks, then detail 23 black box LLM foundation model risks screaming out for regulation, finally providing a bird’s eye view of all 81 LLM risks BIML identified. BIML’s first work, published in January 2020 presented an in-depth ARA of a generic machine learning process model, identifying 78 risks. In this talk, I consider a more specific type of machine learning use case—large language models—and report the results of a detailed ARA of LLMs. This ARA serves two purposes: 1) it shows how our original BIML-78 can be adapted to a more particular ML use case, and 2) it provides a detailed accounting of LLM risks. At BIML, we are interested in “building security in” to ML systems from a security engineering perspective. Securing a modern LLM system (even if what’s under scrutiny is only an application involving LLM technology) must involve diving into the engineering and design of the specific LLM system itself. This ARA is intended to make that kind of detailed work easier and more consistent by providing a baseline and a set of risks to consider.
Gary McGraw is co-founder of the Berryville Institute of Machine Learning where his work focuses on machine learning security. He is a globally recognized authority on software security and the author of eight best selling books on this topic. His titles include Software Security, Exploiting Software, Building Secure Software, Java Security, Exploiting Online Games, and 6 other books; and he is editor of the Addison-Wesley Software Security series. Dr. McGraw has also written over 100 peer-reviewed scientific publications. Gary serves on the Advisory Boards of Calypso AI, Legit, Irius Risk, Maxmyinterest, and Red Sift. He has also served as a Board member of Cigital and Codiscope (acquired by Synopsys) and as Advisor to CodeDX (acquired by Synopsys), Black Duck (acquired by Synopsys), Dasient (acquired by Twitter), Fortify Software (acquired by HP), and Invotas (acquired by FireEye). Gary produced the monthly Silver Bullet Security Podcast for IEEE Security & Privacy magazine for thirteen years. His dual PhD is in Cognitive Science and Computer Science from Indiana University where he serves on the Dean’s Advisory Council for the Luddy School of Informatics, Computing, and Engineering.
BIML turned out in force for a version of the LLM Risks presentation at ISSA NoVa.
BIML showed up in force (that is, all of us). We even dragged along a guy from Meta.
The ISSA President presents McGraw with an ISSA coin.
Though we appreciate Microsoft sponsoring the ISSA meeting and lending some space in Reston, here is what BIML really thinks about Microsoft’s approach to what they call “Adversarial AI.”
No really. You can’t even begin to pretend that “red teaming” is going to make anything better with Machine Learning Security.
Team Dinner.
Here is the abstract for the LLM Risks talk. We love presenting this work. Get in touch.
10, 23, 81 — Stacking up the LLM Risks: Applied Machine Learning Security
I present the results of an architectural risk analysis (ARA) of large language models (LLMs), guided by an understanding of standard machine learning (ML) risks previously identified by BIML in 2020. After a brief level-set, I cover the top 10 LLM risks, then detail 23 black box LLM foundation model risks screaming out for regulation, finally providing a bird’s eye view of all 81 LLM risks BIML identified. BIML’s first work, published in January 2020 presented an in-depth ARA of a generic machine learning process model, identifying 78 risks. In this talk, I consider a more specific type of machine learning use case—large language models—and report the results of a detailed ARA of LLMs. This ARA serves two purposes: 1) it shows how our original BIML-78 can be adapted to a more particular ML use case, and 2) it provides a detailed accounting of LLM risks. At BIML, we are interested in “building security in” to ML systems from a security engineering perspective. Securing a modern LLM system (even if what’s under scrutiny is only an application involving LLM technology) must involve diving into the engineering and design of the specific LLM system itself. This ARA is intended to make that kind of detailed work easier and more consistent by providing a baseline and a set of risks to consider.
BIML wrote an article for IEEE Computer describing 23 Black Box Risks found in LLM Foundation models. In our view, these risks determine perfect targets for government regulation of LLMs. Have a read. You can also fetch the article from the IEEE.
Video Interview: A Deep Dive into Generative AI and Cybersecurity
CalypsoAI produced a video interview in which I hosted Jim Routh and Neil Serebryany. We talked all about AI/ML security at the enterprise level. The conversation is great. Have a listen.
Dr. McGraw recently visited Stockholm, Oslo, and Bergen, hosting events in all three cities.
In Stockholm, a video interview was added in addition to a live breakfast presentation. Here are some pictures of the presenter’s view of the video shoot.
Reactions were scary!
The talk in Oslo was packed, with lots of BIML friends in the audience.
Bergen had a great turnout too, with a very interactive audience including academics from the university.
Here’s the best slide from the Bergen talk.
If your organization would like to host a BIML talk, please get in touch.
Here is the talk abstract. If you or your organization are interested in hosting this talk, please let us know.
10, 23, 81 — Stacking up the LLM Risks: Applied Machine Learning Security
I present the results of an architectural risk analysis (ARA) of large language models (LLMs), guided by an understanding of standard machine learning (ML) risks previously identified by BIML in 2020. After a brief level-set, I cover the top 10 LLM risks, then detail 23 black box LLM foundation model risks screaming out for regulation, finally providing a bird’s eye view of all 81 LLM risks BIML identified. BIML’s first work, published in January 2020 presented an in-depth ARA of a generic machine learning process model, identifying 78 risks. In this talk, I consider a more specific type of machine learning use case—large language models—and report the results of a detailed ARA of LLMs. This ARA serves two purposes: 1) it shows how our original BIML-78 can be adapted to a more particular ML use case, and 2) it provides a detailed accounting of LLM risks. At BIML, we are interested in “building security in” to ML systems from a security engineering perspective. Securing a modern LLM system (even if what’s under scrutiny is only an application involving LLM technology) must involve diving into the engineering and design of the specific LLM system itself. This ARA is intended to make that kind of detailed work easier and more consistent by providing a baseline and a set of risks to consider.
Tech Target Podcast: BIML Discusses 23 Black Box LLM Foundation Model Risks
A recently-released podcast features a in-depth discussion of BIML’s recent LLM Risk Analysis, defining terms in easy to understand fashion. We cover what exactly a RISK IS, whether open source LLMs make any sense, how big BIG DATA really is, and more.
