As a part of an ongoing effort to maintain you knowledgeable about our newest work, this weblog publish summarizes some current publications from the SEI within the areas of counter synthetic intelligence (AI), coordinated vulnerability disclosure for machine studying (ML) and AI, safe improvement, cybersecurity, and synthetic intelligence engineering.
These publications spotlight the newest work from SEI technologists in these areas. This publish features a itemizing of every publication, authors, and hyperlinks the place they are often accessed on the SEI web site.
Counter AI: What Is It and What Can You Do About It?
By Nathan M. VanHoudnos, Carol J. Smith, Matt Churilla, Shing-hon Lau, Lauren McIlvenny, and Greg Touhill
Because the strategic significance of AI will increase, so too does the significance of defending these AI programs. To know AI protection, it’s needed to grasp AI offense—that’s, counter AI. This paper describes counter AI. First, we describe the applied sciences that compose AI programs (the AI Stack) and the way these programs are in-built a machine studying operations (MLOps) lifecycle. Second, we describe three sorts of counter-AI assaults throughout the AI Stack and 5 risk fashions detailing when these assaults happen inside the MLOps lifecycle.
Lastly, based mostly on Software program Engineering Institute analysis and apply in counter AI, we give two suggestions. In the long run, the sphere ought to spend money on AI engineering analysis that fosters processes, procedures, and mechanisms that cut back the vulnerabilities and weaknesses being launched into AI programs. Within the close to time period, the sphere ought to develop the processes essential to effectively reply to and mitigate counter-AI assaults, reminiscent of constructing an AI Safety Incident Response Group and lengthening current cybersecurity processes just like the Laptop Safety Incident Response Group Providers Framework.
Learn the SEI white paper.
Classes Realized in Coordinated Disclosure for Synthetic Intelligence and Machine Studying Techniques
by Allen D. Householder, Vijay S. Sarvepalli, Jeff Havrilla, Matt Churilla, Lena Pons, Shing-hon Lau, Nathan M. VanHoudnos, Andrew Kompanek, and Lauren McIlvenny
On this paper, SEI researchers incorporate a number of classes discovered from the coordination of synthetic intelligence (AI) and machine studying (ML) vulnerabilities on the SEI’s CERT Coordination Middle (CERT/CC). Additionally they embrace their observations of public discussions of AI vulnerability coordination circumstances.
Threat administration inside the context of AI programs is a quickly evolving and substantial area. Even when restricted to cybersecurity threat administration, AI programs require complete safety, reminiscent of what the Nationwide Institute of Requirements and Expertise (NIST) describes in The NIST Cybersecurity Framework (CSF).
On this paper, the authors deal with one a part of cybersecurity threat administration for AI programs: the CERT/CC’s classes discovered from making use of the Coordinated Vulnerability Disclosure (CVD) course of to reported “vulnerabilities” in AI and ML programs.
Learn the SEI white paper.
On the Design, Growth, and Testing of Trendy APIs
by Alejandro Gomez and Alex Vesey
Software programming interfaces (APIs) are a elementary part of recent software program purposes; thus, practically all software program engineers are designers or customers of APIs. From meeting instruction labels that present reusable code to the highly effective web-based software programming interfaces (APIs) of immediately, APIs allow highly effective abstractions by making the system’s operations obtainable to customers, whereas limiting the small print of how the APIs are applied and thus enhancing flexibility of implementation and facilitating replace.
APIs present entry to difficult performance inside giant codebases labored on by dozens if not a whole lot of individuals, typically rotating out and in of initiatives whereas concurrently coping with altering necessities in an more and more adversarial setting. Beneath these situations, an API should proceed to behave as anticipated; in any other case, calling purposes inherit the unintended conduct the API system offers. As programs develop in complexity and measurement, the necessity for clear, concise, and usable APIs will stay.
On this context, this white paper addresses the next questions regarding APIs:
- What’s an API?
- What components drive API design?
- What qualities do good APIs exhibit?
- What particular socio-technical points of DevSecOps apply to the event, safety, and operational assist of APIs?
- How are APIs examined, from the programs and software program safety patterns viewpoint?
- What cybersecurity and different finest practices apply to APIs?
Embracing AI: Unlocking Scalability and Transformation By way of Generative Textual content, Imagery, and Artificial Audio
by Tyler Brooks, Shannon Gallagher, and Dominic A. Ross
The potential of generative synthetic intelligence (AI) extends nicely past automation of current processes, making “digital transformation” a risk for a quickly rising set of purposes. On this webcast, Tyler Brooks, Shannon Gallagher, and Dominic Ross intention to demystify AI and illustrate its transformative energy in reaching scalability, adapting to altering landscapes, and driving digital innovation. The audio system discover sensible purposes of generative textual content, imagery, and artificial audio, with an emphasis on showcasing how these applied sciences can revolutionize many sorts of workflows.
What attendees will study:
- Sensible purposes of generative textual content, imagery, and artificial audio
- Impression on the scalability of instructional content material supply
- How artificial audio is remodeling AI training
Evaluating Massive Language Fashions for Cybersecurity Duties: Challenges and Finest Practices
by Jeff Gennari and Samuel J. Perl
How can we successfully use giant language fashions (LLMs) for cybersecurity duties? On this podcast, Jeff Gennari and Sam Perl focus on purposes for LLMs in cybersecurity, potential challenges, and suggestions for evaluating LLMs.
Take heed to/view the podcast.
Utilizing High quality Attribute Situations for ML Mannequin Check Case Era
by Rachel Brower-Sinning, Grace Lewis, Sebastián Echeverría, and Ipek Ozkaya
Testing of machine studying (ML) fashions is a rising problem for researchers and practitioners alike. Sadly, present apply for testing ML fashions prioritizes testing for mannequin operate and efficiency, whereas typically neglecting the necessities and constraints of the ML-enabled system that integrates the mannequin. This restricted view of testing can result in failures throughout integration, deployment, and operations, contributing to the difficulties of transferring fashions from improvement to manufacturing. This paper presents an strategy based mostly on high quality attribute (QA) eventualities to elicit and outline system- and model-relevant take a look at circumstances for ML fashions. The QA-based strategy described on this paper has been built-in into MLTE, a course of and power to assist ML mannequin take a look at and analysis. Suggestions from customers of MLTE highlights its effectiveness in testing past mannequin efficiency and figuring out failures early within the improvement course of.
Learn the convention paper.
