Year: 2017
Type: preprint
Abstract: Ongoing research has proposed several methods to defend neural networks against adversarial examples, many of which researchers have shown to be ineffective. We ask whether a strong defense can be created by combining multiple (possibly weak) defenses. To answer this question, we study three defenses that follow this approach. Two of these are recently proposed defenses that intentionally combine components designed to work well together. A third defense combines three independent defenses. For all the components of these defenses and the combined defenses themselves, we show that an adaptive adversary can create adversarial examples successfully with low distortion. Thus, our work implies that ensemble of weak defenses is not sufficient to provide strong defense against adversarial examples.
Source: arXiv (Cornell University)
Institution: University of California, Berkeley
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: CPS: Frontiers: Collaborative Research: Foundations of Resilient CybEr-Physical Systems (FORCES), CPS: Frontiers: Collaborative Research: Foundations of Resilient CybEr-Physical Systems (FORCES), TWC: Medium: Collaborative: Aspire: Leveraging Automated Synthesis Technologies for Enhancing System Security, CPS: Frontiers: Collaborative Research: Foundations of Resilient CybEr-Physical Systems (FORCES), CPS: Frontiers: Collaborative Research: Foundations of Resilient CybEr-Physical Systems (FORCES)
OpenAlex ID: W2625220439
