spam filtering
Wow! This is pretty cool. Ron Amadeo from ARS Technica reports on a significant, AI-based spam filter update at Gmail. Gmail can now understand “adversarial text manipulations” using a new mechanism called RETVec (Resilient & Efficient Text Vectorizer), meaning that it basically renders graphics of everything written to compare it all for spam classification purposes, based on the words and other bits extracted from the message, basically regardless of how they’re encoded. Using emojis to trick people in spam, because writing something it out in words will get you blocked? That might not fly now. Using cyrillic characters (that look visually similar to a user but look different to a text classifier) to try to skate by Gmail filters and hide the nature of what you’re sending? Nuh-uh. (Interestingly, I’ve known for a while now that Gmail can take issue with certain special characters or emojis in certain places in
Gmail has very recently unveiled a series of new deferral/rejection messages. You’ll want to familiarize yourself with the following Gmail rejection messages: 421 4.7.28 Our system has detected an unusual rate of unsolicited mail originating from your IP address. To protect our users from spam, mail sent from your IP address has been temporarily rate limited. Please visit https://support.google.com/mail/?p=UnsolicitedRateLimitError to review our Bulk Email Senders Guidelines. – gsmtp 421 4.7.28 Gmail has detected an unusual rate of unsolicited mail containing one of your URL domains. To protect our users from spam, mail with the URL has been temporarily rate limited. Please visit https://support.google.com/mail/?p=UnsolicitedRateLimitError to review our Bulk Email Senders Guidelines. – gsmtp 421 4.7.28 Gmail has detected an unusual rate of unsolicited mail originating from your SPF domain. To protect our users from spam, mail sent from your domain has been temporarily rate limited. Please visit https://support.google.com/mail/?p=UnsolicitedRateLimitError to review our
Multiple folks are warning that internet security company Cyren is on the verge of shutting down. The company itself has not exactly said this, but reading between the lines, it seems inevitable; just about all staff laid off, and smart industry folks warning that while servers are up for now, if something were to break, there’s probably nobody left on the payroll to fix it. Cyren is broadly used for spam/content filtering and if your company or mailbox provider utilizes Cyren for inbound spam/security filtering of email, they’re probably scrambling to find an alternate solution. Indeed, one mailbox provider I’ve talked to today is in this exact position, seeing how quickly they can migrate away from the use of Cyren services. Threat intelligence and spam filtering requires that filter rules and fingerprints be updated automatically and periodically, both to capture new threats and address potential false positives. Assuming that there’s nobody
Maybe you have seen this in your inbox test results before? Here’s the scenario. Perhaps your inbox placement testing tool has a dozen seed addresses for a specific ISP or mailbox provider. For that provider, for the message you sent, ten of seed addresses show inbox delivery, but the other two seed addresses show spam folder placement. Confusing, right? What IS your reputation at this mailbox provider? Does this count as spam folder placement or inbox placement? And what should you do about it? Read on to find out.This is what I (jokingly) call the Pepsi Challenge. When you see results like this at an ISP or mailbox provider, it’s because the mailbox provider is doing testing, inviting a sample of your (their) subscriber base to provide feedback on your email messages. It’s a taste test, of sorts, where the mailbox provider wants to know if your flavor of email
Let’s compare B2C versus B2B deliverability issues, shall we?In the B2C (business-to-consumer) or DTC (direct-to-consumer) email marketing universe, the number of mailbox providers, while broad, is very heavily concentrated in the US. There are six providers, that when you add up their subscriber reach, they comprise over 90% of almost any typical US B2C email list: Google, Yahoo, Microsoft, Comcast and Apple. Anything beyond the top five is pretty much in the long tail. (That doesn’t mean you ignore deliverability issues for smaller providers, but when you do a cost/benefit analysis of time investment versus reward, it is often clear that fixing an issue with a big provider first will yield more benefit.)In the US B2B (business to business) email universe, things are not as obviously concentrated. There are more providers and it’s not just a set of six controlling just about all of the mailboxes you’ll want to send mail
It’s my first official post for the work blog! With an infographic (sort of) that you can borrow! Over at Kickbox, read about the history of ISP and mailbox provider spam filtering, as remembered by…me! It’s been fun to watch the evolution of email technology, email marketing best practices, spam filtering and more over these past twenty five years. It’s also a good reminder that email is not standing still. It’s not dead tech, it’s not old tech. There’s still new stuff to be learned, every day and every year. Keep learning!That cool graphic I promised? Of course it’s not the one above; I didn’t include it here, as to not spoil the surprise. Click on through to check it out!
Your IP reputation is important. Your domain reputation is important. Your content is important, too.No, really.Well, okay. Of the three, content is third in the ranking. Sometimes a distant third. But it is on the list, and rightly so. Sometimes we here in deliverability land talk about how content doesn’t matter – but that’s not quite correct. Or perhaps it’s more accurate to say that we’re guilty of explaining things too simplistically. Reputation and deliverability success are MOSTLY driven by reputation and reputation is MOSTLY driven by (indirect ISP measures of) permission. Since ISP spam filters can’t really read permission directly, they rely on other signals to try to back into it. And content filtering is a tiny little part of that; trying to infer that a sender is bad because their mail includes content fingerprints or hallmarks that are often found in unsolicited and unwanted mail. Thus, content matters.Here’s…
It’s always good to check your email messages against the popular and free SpamAssassin spam filter (maybe even using my KBXSCORE tool?) to try to minimize your spam score. But sometimes the results can be cryptic, or you get a quite unexpected result. Understanding SpamAssassin’s feedback can sometimes be a bit of a challenge. You get a list of scoring keywords and perhaps a sentence or two about what each one means. But what if you need more? Check out what Deliverability Consultant Nicola Selenu has put together over on his Top Deliverability website: A list of all the SpamAssassin rules, with detailed descriptions and little code snippets showing you what words and tags the filter is often looking for! This is something that I’m definitely bookmarking for future reference. Thanks, Nicola, for compiling and sharing this! It might not make every single spam filter rule easier to understand, but more data leads…
Did you know? Google has a “Sender Contact Form” for Gmail, previously known as the bulk sender contact form.What is it? It’s a way for you to ask Google to reconsider their Gmail filtering decisions for your emails, to give them more information and contact information, hopefully allowing them to improve their spam filtering and perhaps allowing them to reconsider putting your mail in the spam folder or blocking it.Why should you do it? Because every little bit helps. In almost all cases, it will not garner a response, but Google says that they do review all submissions. In some cases, this will cause them to help improve your ability to get mail to the inbox — my understanding being that this submission does create an internal ticket in their system that will be reviewed by the right people.There are caveats to keep in mind here:This is not a fast…
Here’s one I almost missed, from a couple of weeks ago: According to Wired, Cloudflare is moving into the email security space. The goal? To better protect against email-delivered threats (think phishing). They see a gap there; one I’ve noticed myself.From the article Cloudflare Is Taking a Shot at Email Security by Lily Hay Newman: “Prince says that Cloudflare employees have been “astonished by how many targeted threats were getting through Google Workspace,” the company’s email provider. That’s not for lack of progress by Google or the other big providers on anti-spam and anti-malware efforts, he adds. But with so many types of email threats to deal with at once, strategically crafted phishing messages still slip through. So Cloudflare decided to build additional defense tools that both the company itself as well as its customers could use.”I’m using a bit of cheeky hyperbole up there in my choice of title, but…