conference paper

Too Big to FAIL: What You Need to Know Before Attacking a Machine Learning System

Tudor Dumitraş^a✉, Yiğitcan Kaya^a, Radu Mărginean^a, Octavian Suciu^a

^aUniversity of Maryland, College Park, USA
✉Corresponding author

Lecture notes in computer science Springer Science+Business Media2018-01-01 0 citations38 references

Looking for the full paper…

Export

Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.

Abstract

No abstract is available from our sources. Use “Read paper” to view it.

TL;DRThe FAIL model is proposed, which describes the adversary’s knowledge and control along four dimensions: data Features, learning Algorithms, training Instances and crafting Leverage, and allows for systematic comparisons of attacks against ML systems, providing a clearer picture of the security threats that these attacks raise. (Semantic Scholar)

Plain-language summary

AI illustration of the topic of “Too Big to FAIL: What You Need to Know Before Attacking a Machine Learning System”

Too Big to FAIL: What You Need to Know Before Attacking a Machine Learning System

Abstract

Plain-language summary

Discussion