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

Existing methods for generating adversarial code examples face severalchallenges: limted availability of substitute variables, high verificationcosts for these substitutes, and the creation of adversarial samples withnoticeable perturbations. To address these concerns, our proposed approach,RNNS, uses a search seed based on historical attacks to find potentialadversarial substitutes. Rather than directly using the discrete substitutes,they are mapped to a continuous vector space using a pre-trained variable nameencoder. Based on the vector representation, RNNS predicts and selects bettersubstitutes for attacks. We evaluated the performance of RNNS across six codingtasks encompassing three programming languages: Java, Python, and C. Weemployed three pre-trained code models (CodeBERT, GraphCodeBERT, and CodeT5)that resulted in a cumulative of 18 victim models. The results demonstrate thatRNNS outperforms baselines in terms of ASR and QT. Furthermore, theperturbation of adversarial examples introduced by RNNS is smaller compared tothe baselines in terms of the number of replaced variables and the change invariable length. Lastly, our experiments indicate that RNNS is efficient inattacking defended models and can be employed for adversarial training.

A Black-Box Attack on Code Models via Representation Nearest Neighbor Search