Category Archives: Fraud Prevention

Dealing with Account Take Over? Here are my top tips (O’Reilly post)

Online payments and eCommerce have been targets for fraud ever since their inception. The availability of real monetary value coupled with the ability to scale an attack online attracted many users to fraud in order to make a quick buck. At first, fraudsters used stolen credit card details to make purchases online. As services became more widely used, a newer, sometimes easier alternative emerged: account takeover.

Account takeover (ATO) occurs when one user guesses, or has been given, the credentials to another’s value storing account. This can be your online wallet, but also your social networking profile or gaming account. The perpetrator is often someone you don’t know, but it can just as easily be your kid using an account you didn’t log out of. All fall under various flavors of ATO, and are easier than stealing one’s identity; all that’s needed is guessing or phishing a user’s credentials and you’re rewarded with all the value they’ve been able to create through their activity.

Read more on O’Reilly’s programming blog here.

Working on risk and fraud prevention? Don’t dig your career into a hole

I give this talk about Risk Management called The Top 8 Reasons You Have a Fraud Problem. I learn a lot from the way audiences respond to it, mostly from objections. Most commonly, objections tell me how risk managers paint themselves into a corner in day-to-day work, effectively limiting their ability to drive change or participate in key business decisions.

How do they do that?

First, they make losses their one and only benchmark. It’s easy to focus on reducing losses when the business is taking hits, it’s your job and it’s what’s expected of you. But overcompensating and focusing on aggressive loss reduction whenever possible, while rejecting troves of good customers, will not only limits your business’s growth prospects – it turns the risk manager into a single-issue player. Revenue enablement must be a core KPI for the risk team or it will lose relevance.

Second, risk managers focus on maintaining status quo. When one lacks tools and methods to control their environment, their first response is to try to make sure that nothing ever changes. It’s not the risk team’s job to say no to everything new; it’s their job to find a way to say yes. That’s where the technological and organizational edge is. Find ways to enable new business by shifting risk across your portfolio and finding detection and prevention solutions that support even the craziest marketing ideas. You may flail at first but long-term, you’re building an important muscle.

Last, they tend to distrust the customer. It makes sense – when faced mainly (and often solely) with the malfunctions of the operation, often caused by customers themselves, one tends to stop believing in people’s good intention. That starts becoming a problem when every product design process turns into a theoretical cat-and-mouse game where every possible abuse opportunity must be curbed in advance. You should let users be users, and that means that there will be breakage and there will be losses. Zero losses can easily be achieved by stopping all activity in your system; you should accept that some customers will be bad and find a way to detect these as they act in your system, rather than limit every customer’s ability to use your product.

As I often write, risk teams are multidisciplinary and must think about operations, data science, product design and more. Whenever one focuses on limiting risk instead of trusting users, challenging the status quo and enabling new business, they are contributing to turning risk into a control function, a technocratic add-on that doesn’t deserve a seat at the decision makers’ table. Make sure that’s not you.

(If you want to read some concrete advice on how to do that, take a look at my free eBook here)

BitCoin mass-adoption challenges

Crypto currencies, specifically BitCoin, are touted as the next big thing in financial
services. A secured, encrypted, technologically advanced platform that can support
monetary transactions across the globe is a dream come true for a lot of financial
services innovators hoping for a borderless financial world. This wave of innovation,
while still nascent, bears a lot of advantages.

It’s important to note, though, that not everything is green in the realm of BitCoin. While
some disadvantages are obvious – exchange rate volatility and lack of sufficient market
making are two obvious ones – some are less obvious, and are sometimes mistakenly
presented as advantages by newbies to the industry. Specifically, I am referring to fraud
using or on the BitCoin platform, and misconceptions about its feasibility – while some
may think it is much safer than other means of payment, that is absolutely not the case.
With BitCoin’s no-recourse movement of funds, transactions are subject to two types of
fraud: supply side fraud, and social engineering. Their prevalence might hinder mass
adoption of crypto currencies and must be addresses by the ecosystem before those
can be used the proverbial “normals”, the majority of consumers.

When a consumer purchases online using a credit card, the merchant charging the card
isn’t protected from fraud the same way they would be if charging the card in the offline
world. No issuer, acquirer or card network provides any fraud protection and merchants
can easily be victims of stolen cards or “friendly fraud”, a term describing customers
making actual purchases then charging back alleging fraud, while keeping the goods.

Defending oneself from chargebacks is difficult for merchants and fraud constitutes a major line item in retailers’ financial statements. However chargebacks serve a purpose: they
protect consumers from fraudulent merchants, failure to provide service and other
issues. With no ability to reverse transactions, no consumer protection is possible,
hence more and more fraud is perpetrated by those who pretend to be merchants. As
merchants, they can sell a service or product while charging in advance, and never ship
the product (or never own it in the first place). Consumers who pay find themselves out
of their money and the product they were offered, with no ability to reverse a payment.
Thus, demand side fraud becomes much more appealing to fraudsters.

This lack of protection hurts consumer trust. It also amplifies the damage from each
fraud case. A single fraudster using a stolen credit card may shop for $1000 in stolen
goods; a single fraudulent shop can easily scam dozens and hundreds of consumers.

The other thing to consider is social engineering. Fraud wasn’t invented in the 20th
century nor is it dependent on credit cards. There is a reason why Western Union or
MoneyGram was and still is a favorite for 419-type (“Nigerian”) scams; it, too, has no
option to reverse a payment. Every complex system is as strong as its weakest link, and
BitCoin is no different; the human element is its biggest failure point. As the SEC brings
to trial a man accused of running a BitCoin ponzi scheme, it becomes obvious that no
encryption beats greed and no sophisticated technology beats lack of good judgement.
In that sense, BitCoin isn’t different than any other means of payment, for better or for
worse. It is just not any safer.

Crypto-currencies hold a big promise for a more sophisticated financial infrastructure,
but the discussion about them is still limited to a small group of techies. As the world of
those currencies expands to meet the average user, questions regarding consumer
protection and social engineering must be dealt with, otherwise BitCoin will fail to be
adopted. We cannot just trust the users to be sophisticated, as we have all consistently
demonstrated that as a crowd, we are not sophisticated at all. In a sense, the same lack
of a governing 3rd party guaranteeing at least some protection or recourse, justifiably
hailed as the platform’s greatest advantage, is also one of its biggest disadvantages.
That, too, needs to be a part of an informed discussion.

Why using Bitcoin is like abstinence, and other thoughts about cryptocurrency and financial systems

Elad Gil has this brilliant post titled “6 Startup Ideas Every Nerd Has” with a poignant explanation of how these are thought out. As someone who works on macine learning I can tell you that idea #2 repeats itself too often. I, too, have dabbled with ranting about ideas I hear too often. There is yet another type of ideas, though – ideas that are essentially interesting and good but that are too deep in geekdom to be relevant. Cryptocurrency is one of them.

If you work in payments you can’t get away from cryptocurrency, and its poster child Bitcoin. Every talk of fraud in payments draws scoffs from random commenters; Bitcoin will solve your fraud problems, they say. Irreversible, anonymous, plain and clear. Objecting responders talk of Bitcoin’s (lack of) merits as legal tender and the probability that governments will accept a legal tender they don’t control, if only for money laundering control. Both miss the point: Bitcoin isn’t a contender in the race to replace money. Claiming that Bitcoin solves fraud is like claiming that abstinence solves STDs; at zero participation from the general public, proliferation of fraud in Bitcoin is as futile and unadvantageous as being a sexually transmitted disease is in a world full of monks.

If everyone used Bitcoin, there would be ways to defraud people out of it; from Man In The Middle to 419/Nigerian Prince scam to simple MLM, scams and fraud in eCash are as old as eGold. The human factor is the weakest link, and no cryptocash will replace that. Furthermore, the barriers to entry into cryptocash usage, even if it could solve the problem of fraud, are too high, and prevent wide acceptance. The crypto-community likes this difficulty so much, cherishes it so, that wide adoption is impossible. If you disagree, have your mom mine me some bitcoins. I’ll pay more than the $42 they’re asking for in Mt Gox. You know what? Just have her read through the documentation and explain them back to someone who isn’t you.

Is the system broken? No doubt. The problem isn’t in the way legal tenders are minted, though, but in two other places: identity brokers and financial infrastructure.

The brokers – the card issuers – own the financial relationship and data to underwrite consumers for credit. That’s one major part of the financial equation that let financial institutions dictate the rules of the game both online and offline. If you undermine that relationship you get access to one of the most significant relationships consumers in the developed world have. That’s why I love short term credit schemes like Klarna and prepaid card services like; the first creates a financial relationship from thin air by extending credit in real time, and the second encourages consumers to deposit some of their paycheck directly to their prepaid-supporting account. Both have the ability to disintermediate issuers.

The financial infrastructure is where I actually think cryptocurrency can be helpful. No matter what you do you can’t run away from the card networks or clearing houses; they are the backbone of money movement. Every dollar moving around ends up paying tribute to the eternal gods of monetary movement. What if Bitcoin didn’t try to become a replacement for money consumers are using, but rather create the first true cloud based clearing house, where newly created financial institutions trade reserves and foreign currency using the Internet, but securely, rather than using the current broken systems? That for me is a big promise, and one huge problem no one’s tackling. What it would require is large Bitcoin liquidity reserves, backed by real currency, and with a stable enough exchange rate to plan a 12 to 18 months window. If new lenders could borrow in Bitcoin from a central Bitcoin exchange, its way to becoming a de-facto backbone of a new breed of financial transactions will be much more probable. So far, it doesn’t seem remotely as available and stable as required.

The payments and personal finance world is broken, but it enjoys a distorted local maximum that a lot of energy is required to move away from. Simply waving an interesting idea at the public doesn’t work. Like flash players weren’t as popular before the iPod and Napster, while changing the music industry, crashed as a business, cryptocash is a precursor to something, but is still not it. It can go somewhere, but is still not there. We need to recognize that to be able to move ahead.


Fraud in Digital Goods Sales 201 (Signifyd post)

The Signifyd blog has a blog post worth reading today:

Selling digital and virtual goods is a lucrative business, but one that also attracts a lot of fraud attempts. The logic is obvious: no shipping requires no physical presence or appearance of one, fast delivery allows fraudsters to quickly buy multiple items and exploit much more of every stolen card, recourse by the seller is almost impossible due to the speed and finally, reselling stolen products is much easier than tangible goods. After our blog was featured in Balanced’s post about fraud, we saw multiple questions about fraud in digital goods. One of them was this comment on HN. One reason for Signifyd getting a lot of retailer attention is our ability to provide quality fraud prevention decisions that help reduce fraud in cases where there’s little recourse. We wanted to share some insights.

Common wisdom about preventing fraud in digital goods is abound. We’re not looking to repeat the regular tips – using IP address to billing address distance, purchase velocity, email domain type and device fingerprinting as indicators. What we’d like to do is add some more details as to why these things often fail, and suggest a few best practices. Here are some:

  1. Digital goods purchases provide a quick feedback loop, allowing fraudsters to test and learn fast and adapt. Deploying rules with a single threshold or indicator (e.g. number of past purchases over 4, or IP country must match BIN country) and rejecting 100% of purchases immediately simply provides faster feedback. Either compose rules that have multiple indicators, randomly reject less than 100% of purchases, or implement a random delay in your response.
  2. IP to billing address location is a complex indicator. Simply measuring distance won’t work when the network is mobile, and setting a single threshold won’t work in most countries. Use sources like GeoIPOrg to understand what connection this IP comes from, and implement bins to your distance function.
  3. Email domain type is relevant but simplistic. After you weed out the free but rare ones (bad) and corporate emails (usually good) you remin with a ton of Gmails. What then? Using online searches to determine that this email is actually tied to a person is an important next step.
  4. Customer browsing patterns are highly indicative. New customers, returning customers and fraudsters all navigate differently on your website. Count the number of clicks to initiating a purchase, as well as which types of pages new customers pass through. You’ll see obvious patterns emerging.
  5. Don’t wait for chargebacks to come. Have one person on staff reviewing purchases randomly to detect emerging trends and respond to them.
  6. Machine fingerprinting is helpful, but is often a glorified javascript. Build basic matching in house based on information you collect from consumer sessions, and watch for users who look similar to previous ones but always have new cookies. Fraudsters know how to flush cookies – it’s not the linking that gives them away, but rather the attempt to not be detected.
  7. Don’t use 3DS. You will pay much more in lost business than prevent fraud.

Fraud in digital goods is a real problem, but a solvable one. Don’t let the threat of lost money shut down your business and drive you to blocking whole countries from your system. And, give us a buzz. We’d love to see how we can help you.

PayPal, Lenovo and killing the password

I like this new initiative from PayPal and Lenovo. With little software installation it basically turns every device into a random password generator providing another authentication factor. It’s hard to know whether phishing and brute force password hacking are still prevalent issues since most of the data are from solution providers’ FUD campaigns; my view is that the problem is real, however not as big and complex as it’s made to be. Based on my experience in PayPal most hacking activity can be detected through probabilistic means rather than assigning the consumer with more secrets. You can read more about that here.

Will this solution prove useful? Having an app to automatically contribute an authentication factor removes some part of the human factor in the equation, and that is a lot of potential security breaches. No argument there. Still the biggest problem in access control is the human factor, and that is what makes defending against it so complicated, and turns additional authentication factors into a limited solution: people forget, and more often, they compromise themselves.

No matter if simple or complex, secure or un-secure (actually ,more so when secure and complex): if there’s a password, users will forget it, and you will have to offer some kind of password retrieval flow that may not require the secured device. Once you allow going around that requirement, it will be used by fraudsters to access accounts.

The bigger problem is that users compromise themselves. They give their credentials to others, they give their devices to their kids, they use shared devices to access confidential information. They do that because it’s what they need to do in their day to day, this is how they need to use your product. Many times there’s no alternative to sharing credentials since the product itself doesn’t allow shared use (multiple users with different permissions on a mobile device? Hard to imagine) but even when such solutions exit they are hard to use and aren’t taken up by consumers . A good example is shared/linked prepaid child accounts that get loaded with cash by parents. While these solutions exist, their use is rudimentary unless the child already has an established, separate financial relationship. It’s so much easier to just give the kid your card.

The bottom line is that usability trumps security, at least the type of security that adds barriers and authentication factors. The industry is long due on moving to behavioral and probabilistic measures to provide online security, but is definitely lagging. Until such knowledge gets properly dispersed, which may take years, and as a mid-way solution, I definitely like what PayPal and Lenovo are doing.

Using social network data in fraud prevention

Linking to a post I put up on Signifyd‘s blog:

Some of the most common questions we get asked are around social data. How do you use social data in fraud prevention? What’s the right way to leverage social network analysis in fraud investigations and real time decisions? We’ve had to deal with this issue with many of our customers, and found a few major obstacles and some very interesting use cases.

To be able to use social data, you first have to gather and understand it. In Signifyd‘s system, one of the first steps we take for each automated decision is “enrichment”, using a large number of online data sources to augment the consumer’s profile and understand the information we get from you to make the best decision.

The first challenge is getting the data. For many smaller retailers, using social data means using their personal (and sometimes fake) Facebook profile to look at a consumer’s profile and learn more about them, maybe run a few Google searches. Doing so at scale, however, is impossible. We went through dozens of online sources and integrated them through public and private APIs to allow collection of public information into a central repository. Doing that allows Signifyd to gather a lot of small pieces into a concrete mosaic of social data, since not every source will yield results at any given time.

When dealing with social data, one of the most important concerns regards consumers’ privacy. When you use a fake profile to friend a consumer you don’t only harm their privacy but also violate Facebook’s terms of service. Being able to use social sources without violating privacy – collecting publicly available information only, while respecting proper use, and only using it for highly targeted use cases – is what allows us to use social data but make consumers, and the businesses that use Signifyd to inspect those consumers, safe.

Once you cross that off, you’re faced with integrating the data. Social data is that it’s highly fragmented; inferring relationships between different pieces – the consumer’s work place, whether their kid is using their details or whether the provided phone number is indeed theirs – is a complex inference task. It requires normalization of provided data into one common form, fuzzy comparison algorithms and other tricks.

Once you have it, how can social data be used for fraud prevention? At Signifyd, we see it being handy for two main uses:

  1. Identity validation: when you accept payments online, stolen credit cards are common. Many times the fraudster doesn’t have all of the card holder’s details, and they augment what they have with invented details. Emails, phone numbers and occasionally names and parts of the billing address are invented. Using social data, different details can be tied to multiple people or be identified as invalid – using, for example, complex white-pages searches. As a result, identity validation becomes a simpler task.Some of this can be used by your team very easily: using a consumer’s social fingerprints, you can establish whether they’ve had any meaningful activity online and how far back that activity has occurred. Profiles that haven’t existed for more than a few weeks or months are often times connected to fake or stolen identities.
  2. Friendly fraud prevention: friendly fraud, or abuse, often happens when a relative or co-worker uses one’s identity to make a purchase. These cases are more subtle in both detection and handling since the offender is often highly informed – knowing passwords, personal details, and having access to personal devices. By using social data on provided details and behaviors, you can infer that there are actually two different people involved in a certain purchase.One of the basic and common scenarios is when, using the provided email address, you learn that the alleged shopper is grossly underage. That immediately raises the suspicion of a kid using a parent’s details. Tying an email address to a work place, and through it to the IP the consumer has connected from, can allow you to better validate their identity and make sure that their information is not used by a family member.

Social data is complicated to use since it’s unstructured and often lacking. Building a strong portfolio of data sources, integrating them effectively and using the data to make fraud detection decisions is one of the important pillars of Signifyd‘s solutions. Try us out!


Forget Big Data

These are the slides from a talk I gave last week. The gist of it: “Big Data” in Fraud and Risk prevention for payments won’t suffice, and must be augmented by domain experts (including a few notes about reasons for that, a bit about domain experts, and some real life examples). Nothing new for readers of this blog, but you may find the slides or wording helpful.