English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Cyber Physical Systems (cps) are deployed in many mission-critical settings,such as medical devices, autonomous vehicular systems and aircraft controlmanagement systems. As more and more CPS adopt Deep Neural Networks (DeepNeural Network (dnns), these systems can be vulnerable to attacks. . Prior workhas demonstrated the susceptibility of CPS to False Data Injection Attacks(False Data Injection Attacks (fdias), which can cause significant damage. Weidentify a new category of attacks on these systems. In this paper, wedemonstrate that DNN based CPS are also subject to these attacks. Theseattacks, which we call Ripple False Data Injection Attacks (rfdia), use minimalinput perturbations to stealthily change the dnn output. The inputperturbations propagate as ripples through multiple dnn layers to affect theoutput in a targeted manner. We develop an automated technique to synthesizerfdias against DNN-based CPS. Our technique models the attack as anoptimization problem using Mixed Integer Linear Programming (Mixed IntegerLinear Program (milp)). We define an abstraction for dnnbased cps that allowsus to automatically: 1) identify the critical inputs, and 2) find the smallestperturbations that produce output changes. We demonstrate our technique onthree practical cps with two mission-critical applications: an (ArtificalPancreas System (aps)) and two aircraft control management systems (HorizontalCollision Avoidance System (hcas) and Collision Avoidance System-Xu (acas-xu)).

ReLUSyn: Synthesizing Stealthy Attacks for Deep Neural Network Based Cyber-Physical Systems