Darktrace AI interrupts in-progress cyber-attacks, including ransomware, email phishing, and threats to cloud environments. It's able to detect and establish baselines for your organization so it can make the distinction between what is and what isn't normal network activity for your organization. This allows it to tackle complex cyber-attacks as they happen and prevent future cyber-attacks from happening.
N/A
TensorFlow
Score7.6 out of 10
N/A
TensorFlow is an open-source machine learning software library for numerical computation using data flow graphs. It was originally developed by Google.
Darktrace is a product well suited for the vast majority of infrastructures and helps monitoring and responding to threats based on the network in a very elastic way. This is a product based on on-premise infrastructures that hosts its machines locally, of course it can be technically difficult to monitor an entire On-Cloud infrastructure but even there there's room for sensors and monitoring, not to mention the SaaS and mail integration that completes the product.
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info
TensorFlow is great for most deep learning purposes. This is especially true in two domains: 1. Computer vision: image classification, object detection and image generation via generative adversarial networks 2. Natural language processing: text classification and generation. The good community support often means that a lot of off-the-shelf models can be used to prove a concept or test an idea quickly. That, and Google's promotion of Colab means that ideas can be shared quite freely. Training, visualizing and debugging models is very easy in TensorFlow, compared to other platforms (especially the good old Caffe days). In terms of productionizing, it's a bit of a mixed bag. In our case, most of our feature building is performed via Apache Spark. This means having to convert Parquet (columnar optimized) files to a TensorFlow friendly format i.e., protobufs. The lack of good JVM bindings mean that our projects end up being a mix of Python and Scala. This makes it hard to reuse some of the tooling and support we wrote in Scala. This is where MXNet shines better (though its Scala API could do with more work).
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info
Uses it Al model UEBA to detect anomalies in the behaviour of not only the users in a corporate network but also the routers, servers, and endpoints in that network.
Provides a visualisation of both egress and outbound network traffics flowing in and out of the organisation.
Darktrace comes with it autonomous AI model detection and responses capabilities.
Darktrace as an AI next generation NDR solution, prevents ,contains and quarantines malicious traffics from and into the corporate network.
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info
There are few areas that I would say need to be improved; their customer support portal allows you to log tickets with any suggestions or things you feel the product is missing, and they will generally show you how to achieve what you want, or in some cases, introduce it as a feature in a later update.
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info
Theano is perhaps a bit faster and eats up less memory than TensorFlow on a given GPU, perhaps due to element-wise ops. Tensorflow wins for multi-GPU and “compilation” time.
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info
The Darktrace toolset is very expansive, allowing it to handle many different tasks, but this leads to a user interface that is sometimes not at all intuitive. Icons don't always make sense visually, and the associated tool tips do not always provide enough detail on what action the button performs
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info
Darktrace support is excellent in my experience. They send a competent engineer on-site to provide on-boarding training. They were also very responsive in responding to questions and concerns. Having an individual point of contact who is a competent network and security engineer is not a common experience, at least for me.
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info
Community support for TensorFlow is great. There's a huge community that truly loves the platform and there are many examples of development in TensorFlow. Often, when a new good technique is published, there will be a TensorFlow implementation not long after. This makes it quick to ally the latest techniques from academia straight to production-grade systems. Tooling around TensorFlow is also good. TensorBoard has been such a useful tool, I can't imagine how hard it would be to debug a deep neural network gone wrong without TensorBoard.
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info
We did NOT select Darktrace. OSSIM/AlienVault is a more mature product and it provided better intelligence and reporting. The end user interface is much easier to use - and you can tell built form engineers who have had to do the work. My suggestion for anyone considering Darktrace, is to get the price upfront; do a 30/60 onsite trail; and do the same thing, at the same time, with AlienVault. AlientVault will win every time. I say that because that's exactly what I did.
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info
Keras is built on top of TensorFlow, but it is much simpler to use and more Python style friendly, so if you don't want to focus on too many details or control and not focus on some advanced features, Keras is one of the best options, but as far as if you want to dig into more, for sure TensorFlow is the right choice
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info
One big positive is how it helps us with the security assessments that clients have done on us. They are looking to see if we know how we might have unusual/malicious traffic running on the network.
If you have a small network and only need 1 appliance, it can be a good ROI and peace of mind.
You could go down a hole in trying to spend time looking at all of your traffic with this software. You need to focus only on what it is showing as potential bad traffic.
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info
