The realities of AI in cybersecurity: catastrophic forgetting

Issue 2 2021 Cyber Security

There is a lot of hype about the use of artificial intelligence (AI) in cybersecurity. The truth is that the role and potential of AI in security is still evolving and often requires experimentation and evaluation.

Malware detection is the cornerstone of IT security and AI is the only approach capable of learning patterns from millions of new malware samples within a matter of days.

But there’s a catch: should the model keep all malware samples forever for optimum detection but slower learning and updates; or go for selective fine-tuning that enables the model to better keep up with the rate of change of malware, but runs the risk of forgetting older patterns (known as catastrophic forgetting)?

Retraining the whole model takes about one week. A good fine-tuning model should take about one hour to update.

SophosAI wanted to see if it was possible to have a fine-tuning model that could keep up with the evolving threat landscape, learn new patterns but still remember older ones, while minimising the impact on performance. Researcher Hillary Sanders evaluated a number of update options and has detailed her findings in the Sophos AI blog (https://ai.sophos.com/blog/).

The detection dilemma

Keeping detection capabilities up to date is a constant battle. With every step we take towards defending against a malicious attack, adversaries are already developing new ways to get round it, releasing updates with different code or techniques. The result is that hundreds of thousands of new malware samples appear every day.

Detection is made even harder by the fact that the latest-and-greatest malware is rarely completely ‘new’. Instead, it is more likely to be a combination of new, old, shared, borrowed or stolen code and adopted and adapted behaviours. Further, old malware can re-emerge after years in the wilderness, co-opted into an adversary’s latest arsenal to take defences by surprise.

Detection models need to ensure they can continue to detect older malware samples and not just the most recent ones.

Updating AI detection models

When it comes to updating AI detection models with new malware samples, vendors have a choice between two options.

The first is to keep a copy of every sample they might ever want to detect and retrain the model repeatedly on an ever-increasing volume of data. This results in better overall performance, but also slower updates and fewer releases.

The second is to only update the detection model on new samples. This is known as fine-tuning. During each step of the fine-tuning process, the model updates its understanding according to the new knowledge added and the impact of this on the patterns seen overall. As a result, the model can ‘forget’ the old patterns it learned previously (catastrophic forgetting). However, training a model on less data means the model updates faster and can be released more frequently, keeping better pace with the rapid rate of change of malware.

Regardless of the option chosen, the need to keep training AI detection models on new samples is critical.

The patterns that AI learns from malware samples enable it to generalise and detect not only what it was trained on, but also never before seen samples that bear at least some resemblance to the training data. Over time, however, new samples will begin to deviate enough that an old model’s effectiveness will decay and it will need to be updated.

The three detection update options evaluated by Hillary Sanders were:

1. Learning based on a selection of old and new samples

This is called ‘data-rehearsal’ and involves taking a small selection of old samples and mixing them in with the new, never-before-seen training data. Using this, the model is ‘reminded’ of the old information it needed to detect older samples, while at the same time learning to detect the newer ones.

2. Learning rate

This approach involves modifying how quickly the model learns by adjusting how much it can change after seeing any given sample. If the learning rate is too fast (in which case the model can change a lot with each sample added), it will only remember the most recent samples that it has seen. If the learning rate is too slow (the model can change only slightly with each sample added), it takes too long to learn anything. Finding the right trade-off between learning rate, retaining old information and adding new information can be tricky.

3. Elastic Weight Consolidation (EWC)

This approach was inspired by work by Google’s DeepMind in 2017 and it involves using the old model like an elastic spring to ‘pull back’ the new model if it starts to forget. For a more in-depth explanation of how to implement this approach, read Hillary Sanders’ blog post at https://ai.sophos.com/2021/02/02/catastrophic-forgetting-part-1/.

Findings

All three approaches performed better on older malware samples than on newer samples. Both the EWC and learning-rate approaches remove the need and cost of maintaining older data. However, the graph shows that while their future performance (using new data) is stronger than that achieved using the data-rehearsal technique, they don’t perform as well as data-rehearsal when it comes to remembering past data.

Because the data-rehearsal technique enables faster training and update releases, dips in future performance are more short term and therefore less worrying. Overall, the research showed that the data-rehearsal approach offers the best compromise between simplicity, update speed and performance in malware detection modelling.

Conclusion

In the malware detection game, being able to remember the past is almost as important as being able to predict the future. This must be balanced against the cost and speed of updating your model with new information. Data-rehearsal is a simple and effective way to protect the model’s ability to detect old malware while significantly increasing the pace at which you can update and release new models.

Read more at https://ai.sophos.com/




Share this article:
Share via emailShare via LinkedInPrint this page



Further reading:

More is less in cybersecurity
Issue 2 2021 , Cyber Security
Post-pandemic paradox: more solutions do not bring better protection. Despite 80% of organisations running up to 10 different protection and cybersecurity solutions simultaneously, more than 50% of them experienced downtime from data loss last year.

Read more...
Ransomware and Microsoft Exchange Server attacks are surging
Issue 2 2021 , Cyber Security
Check Point Research sees global surges in ransomware attacks, alongside increases in cyberattacks targeting Microsoft Exchange Server vulnerabilities at a time where CISA has raised the alarm about ransomware attacks against Microsoft Exchange servers.

Read more...
Malware disguised as meeting apps spiked by 1067%
Issue 2 2021 , Cyber Security
Atlas VPN analysis reveals that cyber threats disguised as videoconferencing applications jumped by 1067% in a year. The data analysed was provided by Kaspersky.

Read more...
Cyber makes it secure
Issue 2 2021 , Cyber Security
Stas Protassov, Acronis co-founder and technology president comments on the recent hacking of over 150 000 Verkada surveillance cameras.

Read more...
Security patches are not a plan
Issue 2 2021, Galix Group , Cyber Security
Patches are undoubtedly an essential component of a cybersecurity strategy, but with the current digital landscape, with many employees continuing to work from home, patches alone are not sufficient.

Read more...
Sophos unveils XGS firewall appliances
Issue 2 2021 , Cyber Security
Sophos unveils XGS firewall appliances with optimised Transport Layer Security (TLS) inspection in light of new research that identifies a surge in cybercriminals using TLS to carry out attacks.

Read more...
Kaspersky reveals five ways ransomware gangs play today
Issue 2 2021 , Cyber Security
] Over the past few years, the methods cybercriminals use to distribute ransomware has changed dramatically. While a few years ago, they would spread encrypted files on a large scale, today their ransomware attacks have become more focused.

Read more...
Safe, friction-free user interactions
Issue 2 2021 , Cyber Security
F5 announced the addition of new SaaS products to its application security portfolio: Device ID and Shape Recognize make use of unique data and analytics capabilities, streamlining customer experiences by removing login friction for users while guarding against fraud.

Read more...
Educating remote workers on cybersecurity
Issue 2 2021, J2 Software , Cyber Security
Cybercriminals have shifted their focus to vulnerable employees who now work from home and use personal Internet connections, requiring more education of remote workers on cybersecurity and better computer safety practices or risk having their data compromised.

Read more...
Healthcare, cybersecurity and the COVID-19 vaccine supply chain
Issue 2 2021 , Cyber Security
Understanding why the COVID-19 vaccine supply chain is being targeted and how to protect against such attacks is vital for IT leaders who understand that healthcare and cybersecurity must now go hand-in-hand.

Read more...