Amazon Introduces Fraud Detector and CodeGuru (venturebeat.com) 19
Amazon is leveraging machine learning to fight fraud, audit code, transcribe calls, and index enterprise data. From a report: Today during a keynote at its Amazon Web Services (AWS) re:Invent 2019 conference in Las Vegas, the tech giant debuted Amazon Fraud Detector, a fully managed service that detects anomalies in transactions, and CodeGuru, which automates code review while identifying the most "expensive" lines of code. And those are just the tip of the iceberg. With Fraud Detector (in preview), AWS customers provide email addresses, IP addressees, and other historical transaction and account registration data, along with markers indicating which transactions are fraudulent and which are legitimate. Amazon takes that information and uses algorithms -- along with data detectors developed on the consumer business of Amazon's business -- to build bespoke models that recognize things like potentially malicious email domains and IP address formation. After the model is created, customers can create, view, and update rules to enable actions based on model predictions without relying on others.
Hahahahaha (Score:2, Troll)
Re: (Score:2)
Wait... wouldn't a professional liar be good at detecting lies? I mean the moment something sounds like something he would say should be a dead give away.
But perhaps that would be a conflict of interest... should be easy to code as well..
if (words sound like trump) return IsLie;
Re: (Score:2)
"Wait... wouldn't a professional liar be good at detecting lies? "
Only for those recognizing their own lies as lies.
Re: (Score:2)
When people lie they know it. But yea, I do understand what you mean because I swear I have met people that buy their own con. Either way... if you say something you also do not know to be true, as though it is truth/fact then you are still a liar. I don't care if you "think" you know the truth, you never bothered to verify and means you were already lying to yourself before you lied to others.
I work in IT, I know the art of bull shittery intimately as I am required to participate in it from time to time
Should work pretty well actually (Score:2)
That's rich. Amazon trying to sell a "fraud detector".
Should work pretty well, all it has to do is check if an item is listed on Amazon and return a warning if so...
All this time, Amazon Marketplace was just a giant honeypot.
Re: (Score:2)
Physician, heal thyself [amazon.com]!
codeguru.com... (Score:2)
...would like a word.
Hold off on this article for now ... (Score:2)
... because we have just learned that Amazon was blocked in alpha.
Know where we could really use fraud detection? (Score:3, Insightful)
Filtering out all the crap reviews on each and every one of Amazon's product pages. But maybe they're concerned they'd lose 95% of their reviews...
Perfect. Just what Putin ordered. (Score:2)
It is like the over use of antibiotics. You are simply training the bacteria to be more resistant. Bacteria is mindless. The internet crooks are brainy. The crooks will evolve complex evasion techniques much faster.
Re: (Score:2)
Now well funded state actors can use adversarial training
You vastly underestimate just how "well funded" those state actors are. There isn't any need to make fraudulent transactions when you've got taxpayers.
I have to deal with this crap when traveling (Score:2)
My ccs and logins get blocked all the time. Here is a login from Thailand, this customer has never logged from there, block. Here is a login from a new IP block in China, this is risky, block. Here is a login from Taiwan (I am using a VPN in China, you insensitive clods), block. Here is a second-factor SMS that went roaming outside the customer's home country, must be a stolen SIM, block. Here someone it trying to change a flight date and pay with a cc different from that used to pay for the original ticket
So let me see if I understand this right (Score:2)
While I'm on the subject I'm guessing it's not "machine learning" so much as a database
Maybe they can use that on their lightning deals? (Score:2)
I got what looked like a genuine box, and most other things in the box seemed the real deal... except for the phone.
I knew something was wrong right away as the phone was loose in the case. I turned it over to find 1 camera and a finger print reader. It did say Samsung on the back and it matched the pictures of an S9. I turned it on and ot identified as a Samsu
Stil: Zero Star Reviews - Ganged Reviews (Score:3)
This is AWS not Amazon Store (Score:1)