Big CodeLearning from open source
By Rafael Ballestas | August 02, 2019
Machine Learning (
ML) for secure code series
the mantra has always been the same:
to figure out how to leverage the power of
to detect security vulnerabilities in source code,
regardless of the technique,
be it deep learning,
natural language processing, or
In this article we present a new player in the field,
a system that has exactly this purpose,
ML with data flow analysis,
namely in the form of taint analysis.
Taint analysis can come in dynamic and static forms and can be performed at the source and binary levels, but either way, the goal is the same. Start by looking at where input comes from and is controlled by the user, for example, a web app search field. These are named sources in this context. Then, continue to follow the thread to where it gets used by the system in a security-critical fashion, as in using that info to query a database, to continue with the previous example. These points are called sinks.
Along the way in the case of a secure application, data should encounter significant input sanitization or validation. These are called sanitizers in the taint analysis context. However, frequently this does not happen, and thus vulnerabilities arise.
DeepCode’s purpose is to
remove minor difficulties these taint analysis tools may have.
DeepCode does this by learning from the vast quantity
of freely-available, high-quality code in open repositories
such as Github,
a circumstance then dubbed "Big Code".
The tool is easy and free to use.
This provides the added advantage
of also learning from the user’s code,
the suggestions made by the tool, and the user’s feedback
how to fix them, etc).
Another problem with taint analysis is that
sources, sinks, and sanitizers need to be specified by hand,
which is extremely impractical for large-scale projects.
This is another area where
but how is that done?
DeepCode has been called
Grammarly for code.
It claims to be 90% accurate,
and that it understands the intent behind the code.
It also claims to find twice as many issues as other tools,
even some critical ones
SQL injection and path traversal, etc.)
which is something typical static analysis tools do not.
Moreover, it claims to be easy to use,
requiring no configuration.
The tool is friendly. You need only point it to your repository and give the appropriate permissions, and then it will show a dashboard with the issues found. Here is one for Eclipse Che Cloud IDE:
Here we see three instances of a possible
path traversal vulnerability.
In the full dashboard,
we also see how they report
a Server Side Request Forgery (
a Cross Site Scripting (
and a header that leaks technical information
And that’s only the issues tagged as "security".
There are also
API misuse issues,
Thread.run() instead of
general bugs or defects,
and now they even throw lint tools results,
which deal with formatting and presentation issues.
Oh, yes, and every issue comes with a possible fix
you might implement right away.
Quite nice, from the point of view of contributing a new vulnerability report to a project, with no false positives. However when the aim is to find all vulnerabilities, one cannot help but raise the question: is that all? Are these all the security vulnerabilities in a project with more than 300,000 lines of code?
Let us take one of the many
Vulnerable by Design (
we use for training purposes in our
and see how many vulnerabilities come up
DeepCode on them.
By the way, they currently support
besides the original
That leaves us with two apps to try:
the Damn Vulnerable
Damn Small Vulnerable Web
VbD apps are built with
I forked both of these on
signed up for a
and let it run.
DSVW, which is a single
under 100 lines of code,
but still ridden with vulnerabilities,
DeepCode reports zero issues.
Perhaps it does not work as well on such tiny projects.
This is, to say the least, disappointing,
DSVW has no less than 26 different
kinds of vulnerabilities, as per its
three of those have been manually explored and exploited.
Maybe it’s a problem with having so few lines of code,
maybe it’s a
so let’s try the other one:
DVNA, built with
NodeJS with the
specific purpose of demonstrating the
OWASP Top 10 vulnerabilities.
This time around,
DeepCode found 9 issues.
Of those, take out the 3 which come from
and let’s consider the other 6;
API misuses, which are basically "use arrows instead of functions"
and 4 are security vulnerabilities,
and pretty serious ones at that:
Code Injection via
evalfunction in calculator module. Not the same one as in the authors' security guide. Also not yet reported in Writeups This should be researched further.
Technical information leakage via the
X-Powered-Byheader, as in
So, altogether, 3 noteworthy security vulnerabilities,
NodeJS application with more than 7,500 lines of code.
at least 29 different vulnerabilities have been reported in
You can see a
on manual testing vs the
code-as-data tool in there, too,
where it is quite clear that tool misses most of the vulnerabilities as well.
Now for a more realistic test,
let’s try running
DeepCode on some of our own repos, namely, Integrates,
our platform for vulnerability centralization and management and
our vulnerability automation framework.
Python, and actively developed.
As before, the vast majority of issues found by
are of the
API usage kind.
Integrates we see a possible
command injection in the spreadsheet report generation function.
However, this input is not controllable by the user,
so this does not pose a real threat at the moment:
However, the suggestion to sanitize the input
subprocess.call() is not bad.
Who knows if
will later have user-configurable passwords for reports,
or a different vulnerability enables an attacker
to change this parameter.
The other security issue
is in the
Again, probably difficult to exploit,
but should be sanitized anyway.
Asserts, however, the 15 issues
DeepCode are less worrisome, for two reasons:
Of course, all the issues detected by
will be taken care of.
Once again, this confirms our other mantra
we have held in this
Machine Learning (
While automated tools,
may have the potential to do
what a human could not do
in terms of repetitions and scalability,
as of yet, they do not have the malice or creativity
which humans have in finding critical and interesting
V. Raychev. 2018. DeepCode releases the first practical anomaly bug detector.
V. Chibotaru. 2019. Meet the tool that automatically infers security vulnerabilities in Python code. Hackernoon