Artificial Intelligence application bridges cyber skills gap
As technology becomes more advanced, cyber crime has never been a more prominent threat to businesses and other professional organisations.
With the cyber crime cost expected to reach US$6trn globally (US$10.5trn by the end of 2025) it is clear that cybersecurity is becoming a key focus for the future of organisations all over the world.
Click here to see full report - ‘2021 Report: Cyber warfare in the C-Suite’
Security Analysts can focus on more sophisticated attacks
While criminals are becoming more sophisticated, AI is continuously developing to tackle the various threat levels.
Due to the increased amount of data available, AI is able to manage all menial tasks within organisations and find links between relatively minor cyber attacks much faster, than the human analyst, and with no risk of fatigue or human error.
Taking the pressure off cybersecurity personnel will allow many organisations to put their physical resources into managing the larger, more significant attacks.
The skills gap
The self-development capabilities of AI is vital during a current skills shortage in the cybersecurity profession.
And as the demand for cybersecurity positions is rapidly increasing, technology is moving faster than ever in order to bridge the gap in preventing cyber crime.
A 2019 report by Burning Glass Technologies has found that:
- The quantity of cybersecurity job postings has increased by 94% since 2013.
- Despite paying 16% more, cybersecurity jobs take 20% longer to fill than other IT jobs.
- More than half of jobs demanding cybersecurity skills are in fact other IT roles, where security is only part of a broader job description.
- For each cybersecurity opening, there was a pool of only 2.3 employed cybersecurity workers for employers to recruit.
- The industry is increasingly turning to automation for solutions. Demand for automation skills in cybersecurity roles has risen 255% since 2013 and demand for risk management rose 133%.
- Public cloud security and knowledge of the Internet of Things are projected to be the fastest-growing skills in cybersecurity over the next five years.
Confidence in the workforce
A recent government report ‘Cybe r security skills in the UK labour market 2021: findings report’ talks about the current state of cybersecurity recruitment in the UK.
Data collated in this report shows how confident personnel are in various cybersecurity tasks and is said to be in unison with the findings from 2018 and 2020.
“The areas where skill gaps are most prevalent are in setting up configured firewalls, storing or transferring personal data and detecting and removing malware, which is consistent with the 2018 and 2020 results. Nevertheless, only a minority of cyber leads across the business population say they are not confident in carrying out each of these tasks”. - Ipsos MORI - Cyber security skills in the UK labour market 2021: findings report
Facebook Develops AI to Crackdown on Deepfakes
In light of the large tidal wave of increasingly believable deepfake images and videos that have been hitting the feeds of every major social media and news outlet in recent years, global organisations have started to consider the risk factor behind them. While the majority of deepfakes are created purely for amusement, their increasing sophistication is leading to a very simple question: What happens when a deepfake is produced not for amusement, but for malicious intent on a grander scale?
Yesterday, Facebook revealed that it was also concerned by that very question and that it had decided to take a stand against deepfakes. In partnership with Michigan State University, the social media giant presented “a research method of detecting and attributing deepfakes that relies on reverse engineering from a single AI-generated image to the generative model used to produce it.”
The promise is that Facebook’s method will facilitate deepfake detection and tracing in real-world settings, where the deepfake image itself is often the only information detectors have to work with.
Why Reverse Engineering?
Right now, researchers identify deepfakes through two primary methods: detection, which distinguishes between real and deepfake images, and image attribution, which identifies whether the image was generated using one of the AI’s training models. But generative photo techniques have advanced in scale and sophistication over the past few years, and the old strategies are no longer sufficient.
First, there are only so many images presented in AI training. If the deepfake was generated by an unknown, alternative model, even artificial intelligence won’t be able to spot it—at least, until now. Reverse engineering, common practice in machine learning (ML), can uncover unique patterns left by the generating model, regardless of whether it was included in the AI’s training set. This helps discover coordinated deepfake attacks or other instances in which multiple deepfakes come from the same source.
How It Works
Before we could use deep learning to generate images, criminals and other ill-intentioned actors had a limited amount of options. Cameras only had so many tools at their disposal, and most researchers could easily identify certain makes and models. But deep learning has ushered in an age of endless options, and as a result, it’s grown increasingly difficult to identify deepfakes.
To counteract this, Facebook ran deepfakes through a fingerprint estimation network (FEN) to estimate some of their details. Fingerprints are essentially patterns left on an image due to manufacturing imperfections, and they help identify where the image came from. By evaluating the fingerprint magnitude, repetition frequency, and symmetrical frequency, Facebook then applied those constraints to predict the model’s hyperparameters.
What are hyperparameters? If you imagine a generative model as a car, hyperparameters are similar to the engine components: certain properties that distinguish your fancy automobile from others on the market. ‘Our reverse engineering technique is somewhat like recognising [the engine] components of a car based on how it sounds’, Facebook explained, ‘even if this is a new car we’ve never heard of before’.
What Did They Find?
‘On standard benchmarks, we get state-of-the-art results’, said Facebook research lead Tal Hassner. Facebook added that the fingerprint estimation network (FEN) method can be used for not only model parsing, but detection and image attribution. While this research is the first of its kind, making it difficult to assess the results, the future looks promising.
Facebook’s AI will introduce model parsing for real-world applications, increasing our understanding of deepfake detection. As cybersecurity attacks proliferate, and generative AI falls into the hands of those who would do us harm, this method could help the ‘good guys’ stay one step ahead. As Hassner explained: ‘This is a cat-and-mouse game, and it continues to be a cat-and-mouse game’.