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

Machine learning is increasingly used in security-critical applications, suchas autonomous driving, face recognition and malware detection. Most learningmethods, however, have not been designed with security in mind and thus arevulnerable to different types of attacks. This problem has motivated theresearch field of adversarial machine learning that is concerned with attackingand defending learning methods. Concurrently, a different line of research hastackled a very similar problem: In digital watermarking information areembedded in a signal in the presence of an adversary. As a consequence, thisresearch field has also extensively studied techniques for attacking anddefending watermarking methods.  The two research communities have worked in parallel so far, unnoticeablydeveloping similar attack and defense strategies. This paper is a first effortto bring these communities together. To this end, we present a unified notationof black-box attacks against machine learning and watermarking that reveals thesimilarity of both settings. To demonstrate the efficacy of this unified view,we apply concepts from watermarking to machine learning and vice versa. We showthat countermeasures from watermarking can mitigate recent model-extractionattacks and, similarly, that techniques for hardening machine learning can fendoff oracle attacks against watermarks. Our work provides a conceptual linkbetween two research fields and thereby opens novel directions for improvingthe security of both, machine learning and digital watermarking.

Fraternal Twins: Unifying Attacks on Machine Learning and Digital Watermarking