{"id":226968,"date":"2024-10-24T15:47:45","date_gmt":"2024-10-24T07:47:45","guid":{"rendered":"https:\/\/www.grab.com\/sg\/?post_type=editorial&p=226968"},"modified":"2025-02-26T18:23:34","modified_gmt":"2025-02-26T10:23:34","slug":"a-glimpse-into-the-cutting-edge-of-anti-fraud-research","status":"publish","type":"editorial","link":"https:\/\/www.grab.com\/sg\/inside-grab\/stories\/a-glimpse-into-the-cutting-edge-of-anti-fraud-research\/","title":{"rendered":"A glimpse into the cutting edge of anti-fraud research"},"content":{"rendered":"\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t

Digital fraud is a significant risk for Grab. An ecosystem like ours\u2014with millions of daily transactions between merchant-, driver- and delivery partners, and consumers\u2014is a prime target for bad actors.<\/p>

Common fraud attempts we encounter include account takeovers, where fraudsters seek access to legitimate Grab user accounts through phishing or social engineering. Another example is credit card fraud, where criminals use stolen credit card information to transact on the platform.<\/p>

Grab\u2019s Integrity team has been developing its own anti-fraud technology to combat fraud. Our enterprise service, GrabDefence, not only protects Grab\u2019s platform, but is also used by other fintechs in the region, such as Vietnamese mobile wallet Momo and Indonesian P2P lender Julo.<\/p>

(Also read: GrabDefence: Building anti-fraud technology for Southeast Asia\u2019s digital age)<\/a><\/p>

However, digital fraud techniques keep evolving. While tools to detect, prevent, and manage fraud are getting more sophisticated, this can\u2019t be done by one industry player alone. It requires long-term efforts involving multiple stakeholders, including practitioners like Grab, and academics.<\/p>

Pushing boundaries is a team effort<\/h5>

That\u2019s why a couple of us at Grab\u2019s Data Science team are working closely with researchers at the National University of Singapore (NUS) to make breakthroughs in digital fraud research.<\/p>

This effort is funded through a multi-year government-backed research programme called AI Singapore<\/a> (AI SG). Our main research focus under AI SG is to harness the potential of graph-based models and deep learning.\u00a0<\/p>

Because digital fraud affects all of us, we want to share a little on the work we do with AI SG to counter it.<\/p>

Graph-based fraud detection<\/h5>

Let\u2019s start with a key concept: What are graphs, in the fraud research context?<\/p>

You can imagine a graph as a data structure where we connect everything\u2014all the individual data points of users, merchants, partners, and transactions. In contrast, traditional data structures such as tables put all these separate entities into different rows of data, thereby missing out on important connectivity information.<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t
A graph structure can reveal connecitions between data points more effectively than data tables.<\/figcaption>\n\t\t\t\t\t\t\t\t\t\t<\/figure>\n\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t

They are a helpful tool in fraud detection, as they can help us visualise and analyse complex relationships between data points. We deploy deep learning, an artificial intelligence methodology which is particularly good at making sense of large amounts of unstructured data, such as those represented in these graphs.<\/p>

With deep learning models such as graph neural networks (GNNs), we can capture more fraudsters who would have otherwise slipped under the radar.<\/p>

Take credit card fraud as an example. Graphs can help identify potential fraudsters who repeatedly misuse stolen credit card information across numerous fake accounts. Similarly, in the case of money laundering, graphs can reveal suspicious connections where money is funnelled through multiple financial entities repeatedly in order to hide the source of funds.<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t
Uncovering potential money laundering networks with graphs. Left: source bank accounts in pink funnel money to e-wallets in blue. Right: Each e-wallet sends and receives money from multiple other bank accounts. Below: Bank accounts and wallets are interlinked in a web that layers money between each other. <\/figcaption>\n\t\t\t\t\t\t\t\t\t\t<\/figure>\n\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t
<\/figcaption>\n\t\t\t\t\t\t\t\t\t\t<\/figure>\n\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t

With GNNs, instead of examining each connection individually, we can simultaneously consider how connections are related to each other and how they interact. This helps to identify fraud rings more effectively.<\/p>

(Also read: Graph Networks – Striking fraud syndicates in the dark)<\/a><\/p>

Taking graph analysis further<\/h5>

The next stage is where our work with NUS and AI SG comes in\u2014we share the same ambition to improve and innovate the way we work with graphs and GNNs.<\/p>

As an industry player, we emphasise time-to-market and real-world impact, while in our research work with universities we can strive for technical excellence on longer time frames and with more exploratory approaches.<\/p>

One target of our long-term research is improving the robustness, efficiency, and scalability of existing models.<\/p>

For instance, we developed a technique called SPADE+<\/a> which can better handle evolving graphs than previous models. Transaction data on digital platforms like Grab isn\u2019t static; it keeps changing in real-time.<\/p>

To make sense of it effectively, SPADE+ offers ways of not just adding new data, but deleting old data in a smart way. Smart, in this context, means adding and subtracting data adaptively in batches only when potentially fraudulent transactions are detected. This helps to improve overall latency.<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t
Illustration comparing our proposed peeling algorithm IncDG with Spade+ against the standard DG algorithm. IncDG is able to detect fraud much faster and earlier, preventing more fraudulent transactions<\/figcaption>\n\t\t\t\t\t\t\t\t\t\t<\/figure>\n\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t

In a reality where successful fraud attempts can cause substantial financial and reputational damage, the industry requires fraud detection systems capable of acting within hundreds of milliseconds on million-scale graphs.<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t
Comparison of (left) typical graph data augmentation strategy with random noise versus our (right) novel learnable introduction of controlled noise. This strategy results in superior performance in anomaly detection on various graphs. <\/figcaption>\n\t\t\t\t\t\t\t\t\t\t<\/figure>\n\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t

Since the AI SG funding was granted in 2022, we\u2019ve co-authored multiple academic papers, including SPADE+, and presented at prestigious conferences in the machine learning community such as the International Conference on Learning Representations (ICLR) and the International Conference on Very Large Data Bases (VLDB), benefiting the larger scientific community.<\/p>

We have regular check-ins, provide ideas and input to the research team, and serve as a test bed for them to validate their hypotheses.<\/p>

Academic research takes time, which is precisely why we need it. We intend to incorporate some of the models for use in Grab once the research matures.\u00a0<\/p>

Taking a collaborative approach helps achieve impact in a deep and meaningful way, on things that truly matter to the partners we serve.<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t

\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<\/div>\n\t\t","protected":false},"parent":180237,"menu_order":0,"template":"grab21-default","acf":[],"_links":{"self":[{"href":"https:\/\/www.grab.com\/sg\/wp-json\/wp\/v2\/editorial\/226968"}],"collection":[{"href":"https:\/\/www.grab.com\/sg\/wp-json\/wp\/v2\/editorial"}],"about":[{"href":"https:\/\/www.grab.com\/sg\/wp-json\/wp\/v2\/types\/editorial"}],"version-history":[{"count":45,"href":"https:\/\/www.grab.com\/sg\/wp-json\/wp\/v2\/editorial\/226968\/revisions"}],"predecessor-version":[{"id":227389,"href":"https:\/\/www.grab.com\/sg\/wp-json\/wp\/v2\/editorial\/226968\/revisions\/227389"}],"up":[{"embeddable":true,"href":"https:\/\/www.grab.com\/sg\/wp-json\/wp\/v2\/editorial\/180237"}],"wp:attachment":[{"href":"https:\/\/www.grab.com\/sg\/wp-json\/wp\/v2\/media?parent=226968"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}