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

Anti-malware engines are the first line of defense against malicioussoftware. While widely used, feature engineering-based anti-malware engines arevulnerable to unseen (zero-day) attacks. Recently, deep learning-based staticanti-malware detectors have achieved success in identifying unseen attackswithout requiring feature engineering and dynamic analysis. However, thesedetectors are susceptible to malware variants with slight perturbations, knownas adversarial examples. Generating effective adversarial examples is useful toreveal the vulnerabilities of such systems. Current methods for launching suchattacks require accessing either the specifications of the targetedanti-malware model, the confidence score of the anti-malware response, ordynamic malware analysis, which are either unrealistic or expensive. We proposeMalRNN, a novel deep learning-based approach to automatically generate evasivemalware variants without any of these restrictions. Our approach features anadversarial example generation process, which learns a language model via agenerative sequence-to-sequence recurrent neural network to augment malwarebinaries. MalRNN effectively evades three recent deep learning-based malwaredetectors and outperforms current benchmark methods. Findings from applying ourMalRNN on a real dataset with eight malware categories are discussed.

Binary Black-box Evasion Attacks Against Deep Learning-based Static Malware Detectors with Adversarial Byte-Level Language Model