Skip to content

Tadayoshi Kohno Bibliography

The ultimate guide to cryptography, updated from an author team of the world's top cryptography experts.

Cryptography is vital to keeping information safe, in an era when the formula to do so becomes more and more challenging. Written by a team of world-renowned cryptography experts, this essential guide is the definitive introduction to all major areas of cryptography: message security, key negotiation, and key management. You'll learn how to think like a cryptographer. You'll discover techniques for building cryptography into products from the start and you'll examine the many technical changes in the field.

After a basic overview of cryptography and what it means today, this indispensable resource covers such topics as block ciphers, block modes, hash functions, encryption modes, message authentication codes, implementation issues, negotiation protocols, and more. Helpful examples and hands-on exercises enhance your understanding of the multi-faceted field of cryptography.

  • An author team of internationally recognized cryptography experts updates you on vital topics in the field of cryptography
  • Shows you how to build cryptography into products from the start
  • Examines updates and changes to cryptography
  • Includes coverage on key servers, message security, authentication codes, new standards, block ciphers, message authentication codes, and more

Cryptography Engineering gets you up to speed in the ever-evolving field of cryptography.

Title: Robust Physical-World Attacks on Deep Learning Models

Authors:Ivan Evtimov, Kevin Eykholt, Earlence Fernandes, Tadayoshi Kohno, Bo Li, Atul Prakash, Amir Rahmati, Dawn Song

(Submitted on 27 Jul 2017 (v1), last revised 13 Sep 2017 (this version, v4))

Abstract: Although deep neural networks (DNNs) perform well in a variety of applications, they are vulnerable to adversarial examples resulting from small-magnitude perturbations added to the input data. Inputs modified in this way can be mislabeled as a target class in targeted attacks or as a random class different from the ground truth in untargeted attacks. However, recent studies have demonstrated that such adversarial examples have limited effectiveness in the physical world due to changing physical conditions--they either completely fail to cause misclassification or only work in restricted cases where a relatively complex image is perturbed and printed on paper. In this paper, we propose a general attack algorithm--Robust Physical Perturbations (RP2)-- that takes into account the numerous physical conditions and produces robust adversarial perturbations. Using a real-world example of road sign recognition, we show that adversarial examples generated using RP2 achieve high attack success rates in the physical world under a variety of conditions, including different viewpoints. Furthermore, to the best of our knowledge, there is currently no standardized way to evaluate physical adversarial perturbations. Therefore, we propose a two-stage evaluation methodology and tailor it to the road sign recognition use case. Our methodology captures a range of diverse physical conditions, including those encountered when images are captured from moving vehicles. We evaluate our physical attacks using this methodology and effectively fool two road sign classifiers. Using a perturbation in the shape of black and white stickers, we attack a real Stop sign, causing targeted misclassification in 100% of the images obtained in controlled lab settings and above 84% of the captured video frames obtained on a moving vehicle for one of the classifiers we attack.

Submission history

From: Earlence T Fernandes [view email]
[v1] Thu, 27 Jul 2017 17:37:22 GMT (9143kb,D)
[v2] Sun, 30 Jul 2017 15:58:21 GMT (9128kb,D)
[v3] Mon, 7 Aug 2017 23:52:10 GMT (9128kb,D)
[v4] Wed, 13 Sep 2017 03:59:56 GMT (8067kb,D)

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)