• Follow us


Can artificial intelligence replace humans in the fight against spam?

Artificial Intelligence (AI) is designed to recreate human intelligence as closely as possible, but machines can only think and act like humans if they have as much information about the world as humans have, which allows them to make the same nuanced decisions.

AI is currently in the forefront of the fight against spam, but the question remains, can it ever take over from humans in combatting spam completely?

Spam filters

While the first ”spammer” in 1978 earned about US$ 14 million, spammers today can only dream of achieving such a high return for a single spam mail. They typically receive only one response for every 12.5 million emails that they send, although they can still earn around $3.5 million over the course of a year.

Since its first occurrence, spam has become increasingly sophisticated in design and subject matter, but for all that, the vast majority of spam emails today have far less chance of making it into an email user’s inbox simply because spam filters are constantly evolving.

In their purest form, basic rules filter out messages with suspect ‘trigger’ words such as ‘shipping’, ‘today’ or ‘100 per cent’ which come from unknown or blacklisted IP addresses. Machine Learning (ML), a branch of AI, allows computers to process data and learn for themselves without being manually programmed.

One way is by using a large amount of data from already recognised spam emails. ML has a baseline ‘normal’ and can look for repeating patterns that are highly likely to be an indicator of spam. The ML algorithm then automatically creates a new rule for the spam filter.

Another way to train spam filters with the help of ML is user feedback. If enough users mark emails containing the word "Shipping!" as unwanted, then the filter learns that this word is a new criterion for spam and automatically creates a new rule for it.

So far so good, but does this mean that AI can ever replace humans altogether? The technology is very advanced and improving all the time, but the best possible spam filter at the moment still relies on human beings and machines working together, rather than in isolation.

Human discretion

The reason why is that machines cannot currently recreate the entire human experience and make decisions based on context, abstract thinking or assumptions, Experienced email security experts - let’s call them ‘spam cops’ - can easily ‘join the dots’ from various pieces of evidence and use their discretion where sometimes a spam rule applies and sometimes it doesn’t.

The issue for AI is that the more you broaden the problem environment, the more limited AI's capability becomes and the more training it needs. Humans may be slower at processing data but they have common sense and reasoning capabilities that enable them to plan and make decisions without having all the information.

One way that humans dig deeper is to cross reference with other activities. So, for example, "Was there a major data breach recently where private data could have been hacked – maybe from a well-known company with millions of subscribers?” Another example is phishing trends. Recently there have been EU GDPR-related phishing scams and a rash of sextortion emails where recipients were threatened with their contacts being sent compromising videos unless a ransom was paid.


In addition to the anti-spam specialists, there is a second human factor in the evaluation of spam: the user. From the user point of view, spam can be classified into three categories. Black spam, which is spam which is either not accepted by the provider’s email servers (because it is delivered by servers on blacklists) or can be detected as unwanted spam by spam filters, Red spam, which contains malicious links (e.g. phishing) or even malware. For both of these categories, the recognition rate is very good across all major email providers, so that users hardly ever see these emails in their inbox.

But then there is a third category: “Graymail”. Users currently have an edge over machines when assessing this third category. Called “Gray”, because it is neither on the black list of blocked senders or on the user’s white list of approved senders, this is email that your spam filter isn’t quite sure what to do with until it’s learned a bit more about it. Some users mark it as spam but others don’t which makes its status ambiguous.

Over time, the spam filter will learn what the recipient considers to be “graymail” based on these actions, as well as by the actions of all other recipients of emails sent from that particular domain name. AI may in the future be able to adjust and improve its reaction to this sort of spam proactively, based on such continuous feedback.

Cooperation not competition

AI accelerates spam detection by the sheer force of its processing power which evaluates huge amounts of data almost in real time. Where AI is focused on one narrow task, where all the rules and scenarios are available to it, it can certainly outrun humans in speed and problem management. But this is not the same as thinking and performing tasks autonomously like a human and thereby lies the difference.

Many developers in fact prefer the term ‘augmented intelligence’ which gets across the message more clearly that AI will be able to improve products and services, not replicate the humans that use them.

Currently AI doesn’t exist in this advanced form although maybe it will one day. Humans and AI can achieve far more when they're cooperating instead of competing.

 Jan Oetjen, MD, GMXImage Credit: PHOTOCREO Michal Bednarek / Shutterstock

Read More

Leave A Comment

More News

Latest ITProPortal news

The best antivirus software of 2019 2019-04-04 10:40:31Software choices to keep your computer safe

Huawei laptop software may have had backdoors 2019-04-04 07:30:00Security experts warn against Matebook management software.

Data breaches more common than rainy days in 2019-04-04 07:00:33Employees are still naive when it comes to cybersecurity.

Facebook app data exposed by third-party developers 2019-04-04 07:00:07Thousands of passwords were sitting on the open web for anyone who knew where to look.

Why business owners need to speak digital to 2019-04-04 06:30:20Many businesses are struggling to keep up with the digital era, the businesses that don’t will eventually shut down.

Industry 4.0 facing major security risks 2019-04-04 06:00:54From USB-borne malware to corrupted CAD files, there's a lot the manufacturing industry needs to care about.

Can AI solve the Brexit problem? 2019-04-04 06:00:54Nobody can solve the problem that is Brexit, but could AI?

Us and them: The DBA – developer conflict 2019-04-04 06:00:00In the past DBAs and developers have not always got on. So why is it changing now?

Energy efficiency: the foundation to building sustainable cities 2019-04-04 05:30:46Reducing energy consumption in the places where most people live and work needs to be top priority.

How tech accelerator programmes are creating the next 2019-04-04 05:00:18Modern business have adapted. The typical ‘9am-5pm’ working day isn’t as common as it once was.

Shining a light on shadow IT with unified 2019-04-04 04:30:43Is your business ignoring the root cause of shadow IT?

Can artificial intelligence replace humans in the fight 2019-04-04 04:00:36AI is becoming less constrained by the limits of human knowledge.

TechRadar: Internet news

Universal Pictures’ movie library will soon get upgraded 2019-04-04 15:19:20Universal Pictures Home Entertainment has joined the group of studios making HDR10+ content for Samsung and Panasonic TVs.

Industry 4.0 suffering major security issues 2019-04-04 14:31:48New research from Trend Micro has shed light on the security risks Industry 4.0 poses to the manufacturing sector.

The first 5G phone: our hands-on with the 2019-04-04 14:10:44Verizon and Motorola launched the world's first 5G phone, and we have one in-hand. Here's what we think of it so far.

Huawei fixes MateBook software following backdoor threat 2019-04-04 13:44:59Huawei has patched a security flaw in its MateBook laptops after it was discovered by Microsoft in January.

Fitbit price cut at Amazon: save $60 on 2019-04-04 13:37:12Amazon has slashed the price of the popular Fitbit Alta activity tracker to $69.

Windows 10 churned out rogue notifications that looked 2019-04-04 12:28:10A Microsoft staffer has dropped a clanger with a major testing (and spelling) fail.

LG TV lineup 2019: every LG TV model 2019-04-04 11:49:33This is the LG TV 2019 lineup – with ThinQ smart TVs, voice assistants, rollable OLEDs, and more AI than you can shake a stick at.

Apple Music finally comes to Amazon speakers in 2019-04-04 11:35:08The service arrived on Amazon speakers in the US at the end of last year.

The best Fitbit Inspire and Inspire HR bands 2019-04-04 11:05:40There are lots of bands available for the Inspire and Inspire HR. These are some of our favorites.

Nintendo Switch finally gets controller with a headphone 2019-04-04 10:27:08The officially licensed controller allows you to customize faceplates and programmable paddles.

The best Huawei P10 deals in April 2019 2019-04-04 09:55:15See all of the best Huawei P10 deals in the UK right now. A cheap Huawei phone to save you some money.

The best free Android apps of 2019 2019-04-04 09:46:24There are way too many free apps out there, so we've trawled through and found the top free ones to download.

TechCrunch » Enterprise

WeWork acquires Managed By Q 2019-04-03 13:24:26Managed By Q, the office management platform based out of New York, has today been acquired by The We Company, formerly known as WeWork. Financial ter

Google Drive adds workflow integrations with DocuSign, K2 2019-04-03 12:31:34Google today announced a few new workflow integrations for its Drive file storage service that’ll bring to the service support for some features

Torch takes $10M to teach empathy to executives 2019-04-03 10:11:53When everyone always tells you “yes,” you can become a monster. Leaders especially need honest feedback to grow. “If you look at ric

Rippling raises $45M at $270M to be the 2019-04-03 09:18:02Parker Conrad’s last startup, Zenefits, drowned in busy work. Now with Rippling, he wants to boil that ocean. Instead of trying to nail one thin

Okta unveils $50M in-house venture capital fund 2019-04-03 09:00:49Okta Ventures wants to fund the next generation of identity, security and privacy startups.

Enterprise blockchain startup Offchain Labs scores $3.7M seed 2019-04-03 09:00:30Two of the issues limiting blockchain adoption in the enterprise has been lack of scalability and privacy. Offchain Labs, a startup that spun out of r

Onfido, which verifies IDs using AI, nabs $50M 2019-04-03 08:10:31Security breaches, where malicious hackers obtain snippets of information that then get used to impersonate individuals in order to gain access to ind

Container security startup Aqua lands $62M Series C 2019-04-03 06:20:27Aqua Security, a startup that helps customers launch containers securely, announced a $62 million Series C investment today led by Insight Partners. E

How to handle dark data compliance risk at 2019-04-02 15:00:51Slack and other consumer-grade productivity tools have been taking off in workplaces large and small — and data governance hasn’t caught u

Densify announces new tool to optimize container management 2019-04-02 11:52:47Densify, a Toronto company that helps customers optimize their cloud resources to control usage and spending, announced a new tool today specifically

FireHydrant lands $1.5M seed investment to bring order 2019-04-02 10:00:46FireHydrant, an NYC startup, wants to help companies recover from IT disasters more quickly, and understand why they happened — with the goal of

Pixeom raises $15M for its software-defined edge computing 2019-04-02 09:30:19Pixeom, a startup that offers a software-defined edge computing platform to enterprises, today announced that it has raised a $15 million funding roun

Disclaimer and Notice:WorldProNews.com is not responsible of these news or any information published on this website.