SofiaITC Mission Critical Solutions Going ATOMIC: Clustering and Associating Attacker Activity at Scale | SofiaITC

Going ATOMIC: Clustering and Associating Attacker Activity at Scale

At FireEye, we work hard to detect, track, and stop attackers. As
part of this work, we learn a great deal of information about how
various attackers operate, including details about commonly used
malware, infrastructure, delivery mechanisms, and other tools and
techniques. This knowledge is built up over hundreds of investigations
and thousands of hours of analysis each year. At the time of
publication, we have 50 APT or FIN groups, each of which have distinct
characteristics. We have also collected thousands of uncharacterized
‘clusters’ of related activity about which we have not yet made any
formal attribution claims. While unattributed, these clusters are
still useful in the sense that they allow us to group and track
associated activity over time.

However, as the information we collect grows larger and larger, we
realized we needed an algorithmic method to assist in analyzing this
information at scale, to discover new potential overlaps and
attributions. This blog post will outline the data we used to build
the model, the algorithm we developed, and some of the challenges we
hope to tackle in the future.

The Data

As we detect and uncover malicious activity, we group
forensically-related artifacts into ‘clusters’. These clusters
indicate actions, infrastructure, and malware that are all part of an
intrusion, campaign, or series of activities which have direct links.
These are what we call our “UNC” or
“uncategorized” groups. Over time, these clusters can grow,
merge with other clusters, and potentially ‘graduate’ into named
groups, such as APT33 or FIN7. This graduation occurs only when we
understand enough about their operations in each phase of the attack
lifecycle and have associated the activity with a state-aligned
program or criminal operation.

For every group, we can generate a summary document that contains
information broken out into sections such as infrastructure, malware
files, communication methods, and other aspects. Figure 1 shows a
fabricated example with the various ‘topics’ broken out. Within each
‘topic’ – such as ‘Malware’ – we have various ‘terms’, which have
associated counts. These numbers indicate how often we have recorded a
group using that ‘term’.

Figure 1: Example group ‘documents’
demonstrating how data about groups is recorded

The Problem

Our end goal is always to merge a new group either into an existing
group once the link can be proven, or to graduate it to its own group
if we are confident it represents a new and distinct actor set. These
clustering and attribution decisions have thus far been performed
manually and require rigorous analysis and justification. However, as
we collect increasingly more data about attacker activities, this
manual analysis becomes a bottleneck. Clusters risk going unanalyzed,
and potential associations and attributions could slip through the
cracks. Thus, we now incorporate a machine learning-based model into
our intelligence analysis to assist with discovery, analysis, and
justification for these claims.

The model we developed began with the following goals:

  1. Create a single,
    interpretable similarity metric between groups
  2. Evaluate
    past analytical decisions
  3. Discover new potential

Figure 2: Example documents highlighting
observed term overlaps between two groups

The Model

This model uses a document clustering approach, familiar in the data
science realm and often explained in the context of grouping books or
movies. Applying the approach to our structured documents about each
group, we can evaluate similarities between groups at scale.

First, we decided to model each topic individually. This decision
means that each topic will result in its own measure of similarity
between groups, which will ultimately be aggregated to produce a
holistic similarity measure.

Here is how we apply this to our documents.

Within each topic, every distinct term is transformed into a value
using a method called term frequency -inverse document frequency, or
This transformation is applied to every unique term for every document
+ topic, and the basic intuition behind it is to:

  1. Increase importance of
    the term if it occurs often with the document.
  2. Decrease the
    importance of the term if it appears commonly across all

This approach rewards distinctive terms such as custom malware
families – which may appear for only a handful of groups – and
down-weights common things such as ‘spear-phishing’, which appear for
the vast majority of groups.

Figure 3 shows an example of TF-IDF being applied to a fictional
“UNC599” for two terms: mal.sogu and
mal.threebyte. These terms indicate the usages of SOGU and
THREEBYTE within the ‘malware’ topic and thus we calculate their value
within that topic using TF-IDF. The first (TF) value is how often
those terms appeared as a fraction of all malware terms for the group.
The second value (IDF) is the inverse of how frequently those terms
appear across all groups. Additionally, we take the natural log of the
IDF value, to smooth the effects of highly common terms – as you can
see in the graph, when the value is close to 1 (very common terms),
the log evaluates to near-zero, thus down-weighting the final TF x IDF
value. Unique values have a much higher IDF, and thus result in higher values.

Figure 3: Breakdown of TF-IDF metric when
evaluated for a single group in regard to malware

Once each term has been given a score, each group is now reflected
as a collection of distinct topics, and each topic is a vector of
scores for the terms it contains. Each vector can be conceived as an
arrow, detailing the ‘direction’ that group is ‘pointing’within that topic.

Within each topic space, we can then evaluate the similarity of
various groups using another method – Cosine
. If, like me, you did not love trigonometry – fear not!
The intuition is simple. In essence, this is a measure of how
parallel two vectors are. As seen in Figure 4, to evaluate two
groups’ usage of malware, we plot their malware vectors and see if
they are pointing in the same direction. More parallel means they are
more similar.

Figure 4: Simplified breakdown of Cosine
Similarity metric when applied to two groups in the malware ‘space’

One of the nice things about this approach is that large and small
vectors are treated the same – thus, a new, relatively small UNC
cluster pointing in the same direction as a well-documented APT group
will still reflect a high level of similarity. This is one of the
primary use cases we have, discovering new clusters of activity with
high similarity to already established groups.

Using TF-IDF and Cosine Similarity, we can now calculate the
topic-specific similarities for every group in our corpus of
documents. The final step is to combine these topic similarities into
a single, aggregate metric (Figure 5). This single metric allows us to
quickly query our data for ‘groups similar to X’ or ‘similarity
between X and Y’. The question then becomes: What is the best way to
build this final similarity?

Figure 5: Overall model flow diagram
showing individual topic similarities and aggregation in to final
similarity matrix

The simplest approach is to take an average, and at first that’s
exactly what we did. However, as analysts, this approach did not sync
well with analyst intuition. As analysts, we feel that some topics
matter more than others. Malware and methodologies should be
more important than say, server locations or target
industries…right? However, when challenged to provide custom
weightings for each topic, it was impossible to find an objective
weighting system, free from analyst bias. Finally, we thought:
“What if we used existing, known data to tell us what the
right weights are?” In order to do that, we needed a lot of known
– or “labeled” – examples of both similar and dissimilar groups.

Building a Labeled Dataset

At first our concept seemed straightforward: We would find a large
dataset of labeled pairs, and then fit a regression model to
accurately classify them. If successful, this model should give us the
weights we wanted to discover.

Figure 6 shows some graphical intuition behind this approach. First,
using a set of ‘labeled’ pairs, we fit a function which best predicts
the data points.

Figure 6: Example Linear regression plot
– in reality we used a Logistic Regression, but showing a linear
model to demonstrate the intuition

Then, we use that same function to predict the aggregate similarity
of un-labeled pairs (Figure 7).

Figure 7: Example of how we used the
trained model to predict final similarity from individual topic similarities.

However, our data posed a unique problem in the sense that only a
tiny fraction of all potential pairings had ever been analyzed.
These analyses happened manually and sporadically, often the result of
sudden new information from an investigation finally linking two
groups together. As a labeled dataset, these pairs were woefully
insufficient for any rigorous evaluation of the approach. We needed
more labeled data.

Two of our data scientists suggested a clever approach: What if we
created thousands of ‘fake’ clusters by randomly sampling from
well-established APT groups? We could therefore label any two samples
that came from the same group as definitely similar, and any two from
separate groups as not similar (Figure 8). This gave us the ability to
synthetically generate the labeled dataset we desperately needed.
Then, using a linear regression model, we were able to elegantly solve
this ‘weighted average’ problem rather than depend on subjective guesses.

Figure 8: Example similarity testing with
‘fake’ clusters derived from known APT groups

Additionally, these synthetically created clusters gave us a dataset
upon which to test various iterations of the model. What if we remove
a topic? What if we change the way we capture terms? Using a large
labeled dataset, we can now benchmark and evaluate performance as we
update and improve the model.

To evaluate the model, we observe several metrics:

  • Recall for synthetic
    clusters we know come from the same original group – how many do we
    get right/wrong? This evaluates the accuracy of a given
  • For individual topics, the ‘spread’ between the
    calculated similarity of related and unrelated clusters. This helps
    us identify which topics help separate the classes best.
  • The accuracy of a trained regression model, as a proxy for the
    ‘signal’ between similar and dissimilar clusters, as represented by
    the topics. This can help us identify overfitting issues as

Operational Use

In our daily operations, this model serves to augment and assist our
intelligence experts. Presenting objective similarities, it can
challenge biases and introduce new lines of investigation not
previously considered. When dealing with thousands of clusters and new
ones added every day from analysts around the globe, even the most
seasoned and aware intel analyst could be excused for missing a
potential lead. However, our model is able to present probable merges
and similarities to analysts on demand, and thus can assist them in discovery.

Upon deploying this to our systems in December 2018, we immediately
found benefits. One example is outlined in this blog
post about potentially destructive attacks
. Since then we have
been able to inform, discover, or justify dozens of other merges.

Future Work

Like all models, this one has its weaknesses and we are already
working on improvements. There is label noise in the way we manually
enter information from investigations. There is sometimes ‘extraneous’
data about attackers that is not (yet) represented in our documents.
Most of all, we have not yet fully incorporated the ‘time of activity’
and instead rely on ‘time of recording’. This introduces a lag in our
representation, which makes time-based analysis difficult. What an
attacker has done lately should likely mean more than what they
did five years ago.

Taking this objective approach and building the model has not only
improved our intel operations, but also highlighted data requirements
for future modeling efforts. As we have seen in other domains,
building a machine learning model on top of forensic data can quickly
highlight potential improvements to data modeling, storage, and
access. Further information on this model can also be viewed in this
from a presentation at the 2018 CAMLIS conference.

We have thus far enjoyed taking this approach to augmenting our
intelligence model and are excited about the potential paths forward.
Most of all, we look forward to the modeling efforts that help us
profile, attribute, and stop attackers.