Litcius/Paper detail

There's always a bigger fish

Jack Cook, Jules Drean, Jonathan Behrens, Mengjia Yan

202229 citationsDOIOpen Access PDF

Abstract

Machine learning has made it possible to mount powerful attacks through side channels that have traditionally been seen as challenging to exploit. However, due to the black-box nature of machine learning models, these attacks are often difficult to interpret correctly. Models that detect correlations cannot be used to prove causality or understand an attack's various sources of information leakage.

Topics & Concepts

ExploitComputer scienceBlack boxArtificial intelligenceMachine learningSide channel attackCausality (physics)Computer securityCryptographyPhysicsQuantum mechanicsNetwork Security and Intrusion DetectionSecurity and Verification in ComputingAdvanced Malware Detection Techniques
There's always a bigger fish | Litcius