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

The financial industry relies on deep learning models for making importantdecisions. This adoption brings new danger, as deep black-box models are knownto be vulnerable to adversarial attacks. In computer vision, one can shape theoutput during inference by performing an adversarial attack called poisoningvia introducing a backdoor into the model during training. For sequences offinancial transactions of a customer, insertion of a backdoor is harder toperform, as models operate over a more complex discrete space of sequences, andsystematic checks for insecurities occur. We provide a method to introduceconcealed backdoors, creating vulnerabilities without altering theirfunctionality for uncontaminated data. To achieve this, we replace a cleanmodel with a poisoned one that is aware of the availability of a backdoor andutilize this knowledge. Our most difficult for uncovering attacks includeeither additional supervised detection step of poisoned data activated duringthe test or well-hidden model weight modifications. The experimental studyprovides insights into how these effects vary across different datasets,architectures, and model components. Alternative methods and baselines, such asdistillation-type regularization, are also explored but found to be lessefficient. Conducted on three open transaction datasets and architectures,including LSTM, CNN, and Transformer, our findings not only illuminate thevulnerabilities in contemporary models but also can drive the construction ofmore robust systems.

Hiding Backdoors within Event Sequence Data via Poisoning Attacks