Boffins build AI that can detect cyber-abuse – and if you don't believe us, YOU CAN *%**#* *&**%* #** OFF

Alternatively, you can try to overpower it with your incredibly amazing sarcasm

Trolls, morons, and bots plaster toxic crap all over Twitter and other antisocial networks. Can machine learning help clean it up?

A team of computer scientists spanning the globe think so. They've built a neural network that can seemingly classify tweets into four different categories: normal, aggressor, spam, and bully – aggressor being a deliberately harmful, derogatory, or offensive tweet; and bully being a belittling or hostile message. The aim is to create a system that can filter out aggressive and bullying tweets, delete spam, and allow normal tweets through. Pretty straight forward.

The boffins admit it's difficult to draw a line between so-called cyber-aggression and cyber-bullying. And the line between normal and aggressive tweets is often blurred: after all, people enjoy ranting about things, from feminism to Brexit to tabs-versus-spaces. Having said that, the goal was to craft a system that can automatically and fairly – and by fairly, we mean consistently – draw a line between each category.

After analyzing more than two million tweets that discussed touchy topics such as Gamergate and gender pay inequality at the BBC, as well as more neutral matters like the NBA, the eggheads selected a sample containing 9,484 tweets, and hand labelled them as normal, aggressor, spam, and bully. Obviously, this means the academics' definition of what is aggressive or bullying forms the basis of the model.

About 80 per cent of these tweets were used to train the recurrent neural network, and the remaining 20 or so per cent was used to test it, according to one of the scientists: Jeremy Blackburn, an assistant computer science professor at Binghamton University in New York. We're told the code could sort the test tweets into the four categories with over 80 per cent accuracy. That is to say, 8 of 10 times, the AI would categorize a tweet as expected by the human boffins.

Their research was published in the journal ACM Transactions on the Web – here's the Arxiv version [PDF]. While it's not revolutionary, it's a good introduction text analysis – and don't forget, it is an academic study.

Cyber-bullying is 'dehumanizing'

The neural network analyses not just the content of a tweet but also the tweeter's profile, and the rate at which they tweeted. All the words are encoded as vectors, and various algorithms were used to determine the overall sentiment or emotion of the message and its sender, and whether or not any curse words were used, plus how many hashtags were included, and the number of followers someone has. All of this information is fed into the network so it can predict the category its human masters would have assigned the tweet.

It’s not easy to pinpoint which features are more indicative of online harassment, Blackburn told El Reg on Monday. “It is not straight forward to describe this because we are differentiating between several categories," he said. "For example, we saw that bullies and aggressors had less time between their tweets than spammers, but similar to spammers, bullies used fewer adjectives than normal users and aggressors.”

Aggressors and bullies were more likely to tweet multiple times and use more hashtags than spammers and normal accounts. Bullies tend to harm others by directing their messages at specific people, whereas aggressors were more likely insult groups of folks. Spammers, on the other hand, are less likely to use abusive language and tend to sell things like smut pics and videos.

“Normal users tend to discuss a variety of topics, such as political and social issues, whereas bully users seem to organize their attacks against important and sensitive issues, such as feminism, religion, and pedophiles, using aggressive and in some cases insulting language. Aggressive users express their negativity on popular topics, such as the ‘brexit’ case, ‘maga’, and the spread of the Zika virus. Spammers typically post inappropriate content in an effort to gain more followers or attract victims to malicious sites of questionable or malicious content,” the team wrote in their paper.

Blackburn said cyberbullying has only recently been taken seriously. “This type of behavior is often dehumanizing, which most rational people would consider a bad thing," he said. "From a more pragmatic point of view, the intensity of this behavior, enabled by the scale of the Web and social media, can and has led to acts of real world violence.

'I radically update my course module almost every year to keep up with the rate of change'


“I think that efforts are being made, but that much more can be done. There are difficult decisions for social media companies to consider. For example, some of the biggest offenders also have large followings on social media; simply silencing these people can have unforeseen consequences.”

The researchers hope to use their model on other platforms, such as YouTube or Facebook, though there are other challenges when using machine learning to tackle hate speech and harassment online.

In previous studies, computer scientists discovered that abusive messages bypassed classifiers if the text contained spelling mistakes. Not all rude comments are hateful, either.

“Understanding sarcasm is difficult, especially because different people and cultures express it in different ways,” noted Blackburn. "We did not examine sarcasm in particular, however our algorithm is designed to be extensible, and we intend to add more linguistic features to it in the future." ®

Send us news

Beware the fury of a database developer torn from tables and SQL

Not so much process privilege rings, more circles of hell

Who, Me? Be careful what humorous messages you leave in your app, for you never know who might see them. Welcome to Who, Me?

Our story today is a return for a reader Regomized as "Philip," who does not have the highest opinion of the sales profession.

"We had three developers," he recalled. "One was responsible for UI, another for the database, and a third for image display and capture."

Continue reading

How to find NPM dependencies vulnerable to account hijacking

Security engineer outlines self-help strategy for keeping software supply chain safe

Following the recent disclosure of a technique for hijacking certain NPM packages, security engineer Danish Tariq has proposed a defensive strategy for those looking to assess whether their web apps include dependencies tied to subvertable email domains.

NPM, acquired by Microsoft's GitHub in March 2020, operates the NPM Registry, an online repository of code libraries that web developers include in their applications. It currently hosts almost two million packages and serves more than 174 billion downloads per month.

The attack described earlier this month by security consultant Lance Vick involves identifying NPM packages managed by email accounts tied to expired domains. By registering the expired domain, the attacker then gains control of any email addresses associated with that domain.

Continue reading

Dell's rugged Latitude 5430 laptop is quick and pretty – but also bulky and heavy

Survives all manner of indiginities in Reg tests but may stuggle to cross over from boots to suits

If you drop Dell's Latitude 5430 laptop from hip height onto vinyl flooring that covers a concrete slab, it lands with a sharp crack, bounces a little, then skitters to a halt. Drop it two meters onto sodden grass and it lands with a meaty squish on its long rear edge. The impact pushes a spray of water and flecks of mud through the crack between the screen and keyboard, with a spot or two of each making it onto the keyboard's ASDF row.

I know this, because I did it. And more.

If you put it in a domestic freezer after that drop onto wet grass, then pull it out after ten minutes, a couple of water and mud flecks freeze into little teardrops on the keyboard. The latch that holds the screen to the body of the laptop takes a little extra effort to open.

Continue reading

Microsoft sounds the alarm on – wait for it – a Linux botnet

Redmond claims the numbers are scary, but won't release them

Microsoft has sounded the alarm on DDoS malware called XorDdos that targets Linux endpoints and servers.

The trojan, first discovered in 2014 by security research group MalwareMustDie, was named after its use of XOR-based encryption and the fact that is amasses botnets to carry out distributed denial-of-service attacks. Over the last six months, Microsoft threat researchers say they've witnessed a 254 percent spike in the malware's activity. 

"XorDdos depicts the trend of malware increasingly targeting Linux-based operating systems, which are commonly deployed on cloud infrastructures and Internet of Things (IoT) devices," Redmond warned

Continue reading

AMD reveals 5nm Ryzen 7000 powered by Zen 4 cores

AM5 socket to bring desktop CPUs to life in late 2022, mid-range laptop CPU to follow

AMD has revealed more details of its Zen 4 processor architecture, a desktop CPU that puts it to work, and a socket to house that product.

The CPUs will be called RYZEN 7000 and feature the Zen 4 architecture, which AMD CEO Lisa Su said is built on a 5nm process by TSMC, doubles cache per core to 1MB, includes instructions tuned to the needs of artificial intelligence applications, and boasts clock speeds than can top 5Ghz.

Zen 4 chiplets will sit in a die built on a 6nm process that integrates RDNA 2 graphics, plus silicon needed to accept DDR5 memory and drive PCIe 5.0 controllers.

Continue reading

South Korean and US presidents gang up on North Korea's cyber-offensives

Less than two weeks into his new gig, Yoon cozies up to Biden as China and DPRK loom

US president Biden and South Korea's new president Yoon Suk Yeol have pledged further co-operation in many technologies, including joint efforts to combat North Korea.

While the US agreed to deploy physical weapons and hold military drills if necessary to defend the South against the North, the pair together vowed to "significantly expand cooperation to confront a range of cyber threats from the DPRK, including but not limited to, state-sponsored cyber-attacks."

This cooperation will include working groups attended by law enforcement and homeland security agencies from both nations.

Continue reading

Broadcom in talks to buy VMware: multiple reports

Michael Dell could be the key to any deal

Broadcom is in early talks to buy VMware, according to The New York Times, Bloomberg, and Reuters.

VMware is not commenting on the matter.

This one is interesting, because the three sources we've linked to above all say they've got the news from "a person familiar with the matter." All say the deal is nowhere near done, a price has not been discussed, and a transaction is far from certain to happen.

Continue reading

Linus Torvalds debuts 'boring old plain' Linux kernel 5.18

Adds 'feature activation' for Intel silicon, but Chipzilla still isn't saying what that means

Linus Torvalds has released version 5.18 of the Linux kernel.

The maintainer-in-chief’s post announcing the release was typical of those he made for each of the eight release candidates: this time around he found no nasty surprises, additions were neither major nor complex, and no glitches impacted the development process.

Torvalds called for developers to "run boring old plain 5.18" before getting excited about the forthcoming version 5.19.

Continue reading

Robotics and 5G to spur growth of SoC industry – report

Big OEMs hogging production and COVID causing supply issues

The system-on-chip (SoC) side of the semiconductor industry is poised for growth between now and 2026, when it's predicted to be worth $6.85 billion, according to an analyst's report. 

Chances are good that there's an SoC-powered device within arm's reach of you: the tiny integrated circuits contain everything needed for a basic computer, leading to their proliferation in mobile, IoT and smart devices. 

The report predicting the growth comes from advisory biz Technavio, which looked at a long list of companies in the SoC market. Vendors it analyzed include Apple, Broadcom, Intel, Nvidia, TSMC, Toshiba, and more. The company predicts that much of the growth between now and 2026 will stem primarily from robotics and 5G. 

Continue reading

Deepfake attacks can easily trick live facial recognition systems online

Plus: Next PyTorch release will support Apple GPUs so devs can train neural networks on their own laptops

In brief Miscreants can easily steal someone else's identity by tricking live facial recognition software using deepfakes, according to a new report.

Sensity AI, a startup focused on tackling identity fraud, carried out a series of pretend attacks. Engineers scanned the image of someone from an ID card, and mapped their likeness onto another person's face. Sensity then tested whether they could breach live facial recognition systems by tricking them into believing the pretend attacker is a real user.

So-called "liveness tests" try to authenticate identities in real-time, relying on images or video streams from cameras like face recognition used to unlock mobile phones, for example. Nine out of ten vendors failed Sensity's live deepfake attacks.

Continue reading

Lonestar plans to put datacenters in the Moon's lava tubes

How? Founder tells The Register 'Robots… lots of robots'

Imagine a future where racks of computer servers hum quietly in darkness below the surface of the Moon.

Here is where some of the most important data is stored, to be left untouched for as long as can be. The idea sounds like something from science-fiction, but one startup that recently emerged from stealth is trying to turn it into a reality. Lonestar Data Holdings has a unique mission unlike any other cloud provider: to build datacenters on the Moon backing up the world's data.

"It's inconceivable to me that we are keeping our most precious assets, our knowledge and our data, on Earth, where we're setting off bombs and burning things," Christopher Stott, founder and CEO of Lonestar, told The Register. "We need to put our assets in place off our planet, where we can keep it safe."

Continue reading