Comment by afo | Hacker News Reader

Comment by afo | Hacker News Reader

Founder of Nomorobo here. We put a stop to all of those annoying robocalls, telemarketers, and spam/scam calls and texts. It's about the only thing that works nowadays.

It's not your imagination - these types of calls are out of control. According to our data, 40% of all calls made in the US are illegal, unwanted spam/scam robocalls. And those "neighbor" spoofed calls (same area code and extension) are especially prevalent now. Beginning last summer, they started to account for ~20% of all robocalls. Before that they were only about 2% of all robocall volume.

The Do Not Call list is almost completely ineffective against these types of calls. It was created 15+ years ago to stop legitimate companies from telemarketing. But today's robocallers are criminals that don't really care about the law. They have one goal - scam people and take their money.

Manually blocking calls will also get you nowhere. And please, for the love of god, don't press a number to get on their alleged "do-not-call" list. That will guarantee that you will get even more robocalls - they know you're a live number now.

On the technical side, our landline service (free) is powered by Twilio and our mobile product is available in both app stores (14 day free trial, $2 bucks a month after that). We're a PHP/Laravel shop and our team is completely remote.

To do the actual detection, our algorithm analyzes over 70M calls per month and adds over 1,300 new numbers to the blacklist every day. We built the world's largest commercial telephony honeypot (300k+ lines) and can detect new attacks within minutes of them starting (even with spoofed numbers). Just last month, Nomorobo stopped over 27 million from reaching people's phones.

I'm happy to answer any other questions that you have about robocalls. I'm kind of the "robocall guy". I won the FTC Robocall challenge back in 2013 and grew Nomorobo to be the leading robocall blocker on the market. I've even testified in front of the US Senate about the robocall epidemic.

T-Mobile offers a spam blocking service that stops calls from reaching my phone, because of that there's no way for me to gauge just how many are being blocked. What is your take on network level spam filtering?

You're blocking 1300 numbers a day. I assume the spammers rotate numbers, so if someone gets a recycled number that was on your list, what happens?

These spammers get connected to the telephone system somehow. Is there nothing that can be done to force the telecom providers to more carefully check the companies they lease mass lines to?

I tried your service before, but the calls spoofed as if they come from my area code and exchange were never blocked. Why is that?

Spam calls infuriate me like little else. I'm glad you're working to stop them but it seems to be something that will require a larger industry and/or government intervention.

Thanks for sharing any insight you have!

T-Mobile actually uses Hiya for that. Samsung uses Hiya as well for their equivalent service.

You could just download the app directly

Actually, First Orion/PrivacyStar powers the T-Mobile spam product. Samsung does partner with Hiya, though.

The spammers rotate through new numbers every few hours. We're actually adding 1,300 new numbers per day and the full blacklist is over 700k entries.

As for getting connected to the phone system - Yeah, they have to jump on the phone network somewhere and, in theory, the best way to stop these guys would be to at the ingress point.

The problem is that the phone system is built for interconnection. Even just one bad actor letting the traffic on spoils the system. Layer on top of that the way the network routes calls through multiple hops through multiple carriers and tracking the calls back to the source is nearly impossible. Throw in common carrier regulations (you can't just willy nilly block calls coming over the network) and it amps up even more. Finally, allow all this to be done for fractions of pennies and you get the perfect storm for robocalls.

As for the neighbor spoofed calls, make sure that you enter your phone number in Nomorobo so that we can make sure we protect the correct number block ([Area Code]-[Exchange]-[0000-9999]). In our initial release, we were only able to identify these calls but not block them. It had to do with blocking calls from families with sequential phone numbers. But, in our last release, if you give the app contact access, we can now scrub those numbers and fully block the neighbor spoofed calls.

It's been a bit of a balancing act between being privacy conscious (not needing your email/phone number/invasive contact access) and getting the job done. The balance that we've struck is this - you don't have to give us any of that and you'll get really good protection. But, if you try out the service and start to trust us more, we can do an even better job.

And finally, yes - it's going to take a lot of effort to tackle this problem. While Nomorobo isn't perfect - admittedly, the sim ring landline version is just a crazy hack that the carriers can't stop - the past 4 years have seen some great progress in the fight.

As more and more people become aware of robocall blockers and we show that it's actually a very safe way to protect people, only then will the larger industry come along (kicking and screaming the entire way).

I’ve been a nomorobo customer for a long time, and I’ve had my full phone number entered in the system from day one. And you’ve had access to my contacts, too.

However, I still get the neighbor scam calls, and it’s one of the most annoying things I deal with on a daily basis.

I’ve been thinking that I should write my own whitelist-only call screening app on top of twilight, and maybe becoming one of your biggest competitors.

That is, unless you want to take this idea and implement it yourselves, and saving me the trouble. ;)

Neat!

There's a business called Pindrop that conduct an analysis of audio data to guess where a call is originating from. The idea being, if a call originates from somewhere like India it'll take roughly a certain route that will produce certain audible artifacts on the line.

They also score a bunch of other stuff. I'd recommend reading the patents their CEO filed if you're interested. It's interesting.

I wondered if you could share, roughly, what your algorithm is doing? Are you also analyzing audio data?

Yeah, those guys are great. I run into them at security conferences all the time. Their tech is mainly aimed at the financial sector to make sure the person calling in is who they say they are.

In our case, we don't/can't analyze the audio stream of consumer calls. We can only work with the meta data of the call.

Our algo comes down pretty hard and fast on calls that come into our honeypot. These numbers have been out of service for years and no one should be calling them. Since these phone lines belong to us, we can do anything we want with them - there's no privacy concerns like there would be with consumer calls.

We answer, record, transcribe, analyze, and classify almost 10k calls per hour coming into our honeypot. Check out https://www.nomorobo.com/lookup. There's been a ton of health insurance scams running this week but the scam du jour changes every day.

When we analyze the call data coming into consumer lines, we have to be a little less aggressive so that we don't accidentally block schools, police, doctors, pharmacies.

The only thing left for humans is to help correct the decisions the algo makes. Sometimes it misses robocalls and sometimes it stops things it shouldn't. People just report them through our app and website.

For historic analysis, we also ingest the FTC & FCC robocall complaint data sources. But it's not really a great data source for the real-time detection algo - It's just too slow to be actionable.

You really have to be detecting robocalls at the moment they come in to have a successful blocking product.

I noticed that under "new robocall recordings" the recordings are all from October 25, 2017. Not sure if this is a bug or you stopped updating them on that date or something.

Right now, we only grab one recording per phone number so that's the date that we recorded it.

But, the response to our sampling system has been really strong so we're expanding that to grab one recording per day per number. That way you can also go back in time and see the different scams that have been sent from the same number.

We're also building some deeper analytics so that you can see call volume by robocaller and graphs that show the changes over time.

I am confused. It is titled as "New robocaller recordings". The newest ones under that section are from October 25, 2017. However, the "Most active robocallers (Past 24 hours)" has records from later than October 25, 2017.

Good catch. I think I know what’s going on and what needs to get fixed. Thanks!

Thanks for catching that one. It's been fixed now.

No questions, just a thanks for making Nomorobo.

What information from potential users do you ask for?... to setup NoMoRobo on landlines.

Sounds interesting. I was hoping to try it out but your app isn't in the Canadian Android app store.

We don’t have enough data to protect Canada yet but we’re working on it. Do you get robocalls from US area codes too?

Very rarely, generally they spoof/set their caller ID to a legitimate number with the same area code and exchange as my own.

Reply on news.ycombinator.com