Ai and Security Resources

I recently gave a presentation at Rhodes House regarding the intersections between AI and cybersecurity. These are some articles, code samples, tools, etc. that I either referenced in the presentation or are related to what we discussed. Hopefully it’s useful both to those of you who were at the presentation and to anyone looking for a decent collection of resources about the relationship between AI and cybersecurity.

Resources from the Presentation

All jupyter notebooks (you can run these in google colab)

https://github.com/pavja2/rail-ai-security

DARPA Cyber Grand Challenge

Main DARPA Event Site: http://archive.darpa.mil/cybergrandchallenge/

DARPA Youtube Playlist: https://www.youtube.com/playlist?list=PL6wMum5UsYvZx2x9QGhDY8j3FcQUH7uY0

Deephack

Github Repository: https://github.com/BishopFox/deephack DEFCON Presentation: https://youtu.be/wbRx18VZlYA

Foolbox

Github Repository: https://github.com/bethgelab/foolbox Academic Paper: https://arxiv.org/abs/1707.04131

Imagenet Database

http://www.image-net.org/

Bad Flamingo

Github Repository: https://github.com/jayelm/bad-flamingo

Hack Cambridge Submission: https://devpost.com/software/bad-flamingo

Real World 3D Adversarials

Blog Post: http://www.labsix.org/physical-objects-that-fool-neural-nets/

Academic Paper: https://arxiv.org/abs/1707.07397

Cracking Captchas

Tutorial: https://medium.com/@ageitgey/how-to-break-a-captcha-system-in-15-minutes-with-machine-learning-dbebb035a710

Related Neural Network Walkthrough: https://medium.com/@ageitgey/machine-learning-is-fun-part-3-deep-learning-and-convolutional-neural-networks-f40359318721

Tay AI

Telegraph Write Up: http://www.telegraph.co.uk/technology/2016/03/24/microsofts-teen-girl-ai-turns-into-a-hitler-loving-sex-robot-wit/

Microsoft Official Statement: https://blogs.microsoft.com/blog/2016/03/25/learning-tays-introduction/

Various Other References and Examples

Toolkits

Cleverhans - Adversarial & Defense Toolkit: https://github.com/tensorflow/cleverhans

Blogs

Useful Intro to Adversarial Examples: https://blog.openai.com/adversarial-example-research/

Discussion of Defending Against Adversarials: http://www.cleverhans.io/security/privacy/ml/2017/02/15/why-attacking-machine-learning-is-easier-than-defending-it.html

Academia

N. Papernot, P. McDaniel, S. Jha, M. Fredrikson, Z. B. Celik and A. Swami, “The Limitations of Deep Learning in Adversarial Settings,” 2016 IEEE European Symposium on Security and Privacy (EuroS&P), Saarbrucken, 2016, pp. 372-387. doi: 10.1109/EuroSP.2016.36

Papernot, Nicolas, Patrick McDaniel, Ian Goodfellow, Somesh Jha, Z. Berkay Celik, and Ananthram Swami. 2017. “Practical Black-Box Attacks Against Machine Learning.” In Proceedings of the 2017 ACM on Asia Conference on Computer and Communications Security, 506–519. ASIA CCS ’17. New York, NY, USA: ACM. https://doi.org/10.1145/3052973.3053009.

J. Sahs and L. Khan, “A Machine Learning Approach to Android Malware Detection,” 2012 European Intelligence and Security Informatics Conference, Odense, 2012, pp. 141-147. doi: 10.1109/EISIC.2012.34