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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

WebAssembly (Wasm) is a low-level binary format for web applications, whichhas found widespread adoption due to its improved performance and compatibilitywith existing software. However, the popularity of Wasm has also led to itsexploitation for malicious purposes, such as cryptojacking, where maliciousactors use a victim's computing resources to mine cryptocurrencies withouttheir consent. To counteract this threat, machine learning-based detectionmethods aiming to identify cryptojacking activities within Wasm code haveemerged. It is well-known that neural networks are susceptible to adversarialattacks, where inputs to a classifier are perturbed with minimal changes thatresult in a crass misclassification. While applying changes in imageclassification is easy, manipulating binaries in an automated fashion to evademalware classification without changing functionality is non-trivial. In thiswork, we propose a new approach to include adversarial examples in the codesection of binaries via instrumentation. The introduced gadgets allow for theinclusion of arbitrary bytes, enabling efficient adversarial attacks thatreliably bypass state-of-the-art machine learning classifiers such as theCNN-based Minos recently proposed at NDSS 2021. We analyze the cost andreliability of instrumentation-based adversarial example generation and showthat the approach works reliably at minimal size and performance overheads.

Madvex: Instrumentation-based Adversarial Attacks on Machine Learning Malware Detection