HF-SCA: Hands-Free Strong Customer Authentication Based on a Memory-Guided Attention Mechanisms
Bibliographic record
Abstract
Strong customer authentication (SCA) is a requirement of the European Union Revised Directive on Payment Services (PSD2) which ensures that electronic payments are performed with multifactor authentication. While increasing the security of electronic payments, the SCA impacted seriously on the shopping carts abandonment: an Italian bank computed that 22% of online purchases in the first semester of 2021 did not complete because of problems with the SCA. Luckily, the PSD2 allows the use of transaction risk analysis tool to exempt the SCA process. In this paper, we propose an unsupervised novel combination of existing machine learning techniques able to determine if a purchase is typical or not for a specific customer, so that in the case of a typical purchase the SCA could be exempted. We modified a well-known architecture (U-net) by replacing convolutional blocks with squeeze-and-excitation blocks. After that, a memory network was added in a latent space and an attention mechanism was introduced in the decoding side of the network. The proposed solution was able to detect nontypical purchases by creating temporal correlations between transactions. The network achieved 97.7% of AUC score over a well-known dataset retrieved online. By using this approach, we found that 98% of purchases could be executed by securely exempting the SCA, while shortening the customer’s journey and providing an elevated user experience. As an additional validation, we developed an Alexa skill for Amazon smart glasses which allows a user to shop and pay online by merely using vocal interaction, leaving the hands free to perform other activities, for example driving a car.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".