pith. the verified trust layer for science. sign in

arxiv: 1708.06939 · v1 · pith:X5NS5QAVnew · submitted 2017-08-23 · 💻 cs.LG · cs.RO· stat.ML

Is Deep Learning Safe for Robot Vision? Adversarial Examples against the iCub Humanoid

classification 💻 cs.LG cs.ROstat.ML
keywords adversarialexamplesdeepnetworksalgorithmsbeenclassificationlearning
0
0 comments X p. Extension
Add this Pith Number to your LaTeX paper What is a Pith Number?
\usepackage{pith}
\pithnumber{X5NS5QAV}

Prints a linked pith:X5NS5QAV badge after your title and writes the identifier into PDF metadata. Compiles on arXiv with no extra files. Learn more

read the original abstract

Deep neural networks have been widely adopted in recent years, exhibiting impressive performances in several application domains. It has however been shown that they can be fooled by adversarial examples, i.e., images altered by a barely-perceivable adversarial noise, carefully crafted to mislead classification. In this work, we aim to evaluate the extent to which robot-vision systems embodying deep-learning algorithms are vulnerable to adversarial examples, and propose a computationally efficient countermeasure to mitigate this threat, based on rejecting classification of anomalous inputs. We then provide a clearer understanding of the safety properties of deep networks through an intuitive empirical analysis, showing that the mapping learned by such networks essentially violates the smoothness assumption of learning algorithms. We finally discuss the main limitations of this work, including the creation of real-world adversarial examples, and sketch promising research directions.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.