Adversarial examples: A survey
2018
Adversarial examples are a phenomenon that have gathered a lot of attention in recent studies. The fact that the addition of very small, but carefully crafted perturbations to the inputs of sophisticated and high performing machine learning models may cause them to make significant errors, is both fascinating and important. A survey of findings connected with adversarial examples is presented and discussed in this paper.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
26
References
3
Citations
NaN
KQI