A Netskope foi nomeada Líder no Quadrante Mágico do Gartner™ de 2022 para Security Service Edge. Obtenha o Relatório

  • Produtos

    Os produtos Netskope são construídos na Netskope Security Cloud.

  • Plataforma

    Visibilidade incomparável e proteção de dados e contra ameaças em tempo real na maior nuvem privada de segurança do mundo.

Netskope é nomeada Líder no Relatório do Quadrante Mágico™ do Gartner de 2022 para SSE

Obtenha o Relatório Vá para a plataforma
Netskope gartner mq 2022 sse leader

A Netskope oferece uma pilha de segurança na nuvem moderna, com capacidade unificada para proteção de dados e ameaças, além de acesso privado seguro.

Explore a nossa plataforma
Birds eye view metropolitan city

Mude para serviços de segurança na nuvem líderes de mercado com latência mínima e alta confiabilidade.

Saiba mais
Lighted highway through mountainside switchbacks

Previna ameaças que muitas vezes contornam outras soluções de segurança usando uma estrutura SSE de passagem única.

Saiba mais
Lighting storm over metropolitan area

Soluções de zero trust para a implementação de SSE e SASE

Saiba mais
Boat driving through open sea

A Netskope permite uma jornada segura, inteligente e rápida para a adoção de serviços em nuvem, aplicações e infraestrutura de nuvem pública.

Saiba mais
Wind turbines along cliffside
  • Customer Success

    Proteja a sua jornada de transformação digital e aproveite ao máximo as suas aplicações na nuvem, na web e privadas.

  • Atendimento ao cliente

    Suporte proativo e o compromisso em otimizar seu ambiente da Netskope e acelerar seu sucesso.

  • Treinamento e certificação

    Os treinamentos da Netskope vão ajudar você a ser um especialista em segurança na nuvem.

Confie na Netskope para ajudar você a enfrentar ameaças emergentes, novos riscos, mudanças tecnológicas, mudanças organizacionais e de rede, e novos requisitos regulatórios.

Saiba mais
Woman smiling with glasses looking out window

Contamos com engenheiros qualificados no mundo todo, com experiências variadas em segurança na nuvem, redes, virtualização, entrega de conteúdo e desenvolvimento de software, prontos para prestar assistência técnica oportuna e de alta qualidade.

Saiba mais Portal de Suporte
Bearded man wearing headset working on computer

Proteja sua jornada de transformação digital e aproveite ao máximo seus aplicativos de nuvem, web e privados com o treinamento da Netskope.

Saiba mais
Group of young professionals working
  • Recursos

    Saiba mais sobre como a Netskope pode ajudá-lo a proteger sua jornada para a nuvem.

  • Blog

    Saiba como a Netskope viabiliza a segurança e a transformação de redes através do security service edge (SSE).

  • Eventos e workshops

    Esteja atualizado sobre as últimas tendências de segurança e conecte-se com seus pares.

  • Security Defined

    Tudo o que você precisa saber em nossa enciclopédia de segurança cibernética.

Podcast Security Visionaries

Episode 11: Empowering People for a Secure Future

Reproduzir o podcast
Black man sitting in conference meeting

Leia as últimas novidades sobre como a Netskope pode viabilizar a jornada Zero Trust e SASE por meio dos recursos do security service edge (SSE).

Leia o Blog
Sunrise and cloudy sky

SASE Week

Netskope is positioned to help you begin your journey and discover where Security, Networking, and Zero Trust fit in the SASE world.

Saiba mais
SASE Week

O que é o Security Service Edge?

Explore o lado de segurança de SASE, o futuro da rede e proteção na nuvem.

Saiba mais
Four-way roundabout
  • Empresa

    Ajudamos você a antecipar os desafios da nuvem, dos dados e da segurança da rede.

  • Por que Netskope

    A transformação da nuvem e o trabalho em qualquer lugar mudaram a forma como a segurança precisa funcionar.

  • Liderança

    Nossa equipe de liderança está fortemente comprometida em fazer tudo o que for preciso para tornar nossos clientes bem-sucedidos.

  • Parceiros

    Fazemos parceria com líderes de segurança para ajudá-lo a proteger sua jornada para a nuvem.

A Netskope possibilita o futuro do trabalho.

Saiba mais
Curvy road through wooded area

A Netskope está redefinindo a nuvem, os dados e a segurança da rede para ajudar as organizações a aplicar os princípios de Zero Trust para proteger os dados.

Saiba mais
Switchback road atop a cliffside

Pensadores, construtores, sonhadores, inovadores. Juntos, fornecemos soluções de segurança na nuvem de última geração para ajudar nossos clientes a proteger seus dados e seu pessoal.

Meet our team
Group of hikers scaling a snowy mountain

A estratégia de comercialização da Netskope, focada em Parcerias, permite que nossos Parceiros maximizem seu crescimento e lucratividade enquanto transformam a segurança corporativa.

Saiba mais
Group of diverse young professionals smiling
Blog Plataforma, Produtos, & Serviços The Eight “Must-Haves” for Successful Anomaly Detection
Feb 10 2016

The Eight “Must-Haves” for Successful Anomaly Detection

Traditional anomaly detection methods are either rule-based, which doesn’t generalize well since the rules are too specific to cover all possible scenarios or time-series based, (time vs. quantity) which is too low-dimensional to capture the complexity of real life. Real-life events have higher dimensions (time, both source and destination locations, activity-type, object-acted on, app used, etc.) A successful anomaly detection system will have eight “must-have” features.

Before we go through those features, at the highest level the system must be one that “allows” rather than “blocks” and is based on machine learning.

The reason why an allow list is critical is because it studies the good guys. Bad guys try to hide and outsmart block-based platforms like anti-malware. A successful machine-learning anomaly detection system won’t chase bad guys, looking for “bad-X” in order to react with “anti-X.” Instead, such a platform that is allow-based can study what is stable (good guys’ normal behavior) and then look out for outliers. This approach avoids engaging in a perpetual and futile arms race.

If you’re going to do anomaly detection the right way, you need to be able to scale to billions of events per day and beyond. It’s not practical at that scale to define allow lists a-priori, or keep a perfect history of all observed behavior combinations. Instead, anomaly detection models should be “soft” in the sense that they always deal with conditional probabilities of event features and are ever-evolving.

The second high-level requirement is that a successful anomaly detection system must be machine learning-based. Virtually every CASB today uses this term, but few mean it. Machine learning means just what it says, that pattern recognition should be done by the computer without being specifically told what to look for. There are two main types of machine learning: Supervised and unsupervised. The former is where the computer learns from a dataset of labeled training data whereas the latter is where the computer makes sense of unlabeled data and finds patterns that are hard to find otherwise. Both supervised and unsupervised machine learning are relevant for this blog, and from here on out I’ll simply refer to anomaly detection as “Machine Learned Anomaly Detection,” or “MLAD” for short.

Now that we have established some high-level requirements, let’s dive into the eight “must-haves” for effective MLAD.

Noise resistance: A common issue with all anomaly detection systems is false-positives. In reality, it’s hard to avoid false positives entirely because in the real world there’s always an overlap between two distributions with unbounded ranges and different means. The chart below, which includes two distributions from the same data set of test results, shows this. Move the criterion threshold value to the right and you get fewer false-positives (FPs). The problem is that by doing this you’ll be also getting a growing number of false negatives (FNs). There is always a tradeoff.

While it is difficult to avoid false-positives, a successful MLAD system will take steps to help the user filter noise. Applying this model to cloud security, observing new users or devices, by definition, will generate patterns that are seen for the first time (a new IP address, a new application, a new account, etc. will appear). Good MLAD will learn source habits over time and flag anomalies only when, statistically, the event stream from a source, such as a user or device, is considered seasoned, or established enough.

More critically, MLAD must support a likelihood metric per event. Operators can display only the top N most unlikely/unusual events, sorted in descending order, while automatically filtering out any other event with a less than “one in a thousand,” or “one in a million” estimated probability to occur. Often these per-event likelihood metrics are based on the machine-learned statistical history of parameter values and their likelihood to appear together in context, for any source. It is up to the user to set the sensitivity thresholds to display what they want to see. This type of approach flags “rareness” and not “badness.”

Multi-dimensionality and generality: Successful MLAD platforms don’t rely on specific, hard-wired rules. Machine-learned anomalies are no longer unidimensional, such as “location-based,” “time-based,” etc. Instead, they are designed to detect anomalies in multiple, multi-dimensional spaces. You must look at every feature you can collect and that makes sense in every event and consider many features as a whole when calculating the likelihoods of each combination. An anomaly may be triggered due to one unusual value in a dimension, or a combination of multiple dimensions falling out of bounds. Features can be categorical or numeric, ordered or not, cyclical or not, monotonic or non-monotonic.

Worlds in deep space

Robustness and ability to cope with missing data: Traditional batch machine learning clustering methods suffer from two critical issues:

  • They break in the face of incomplete data, such as missing dimensions in some events.
  • Due to the curse of dimensionality and the way distance metrics between multi-dimensional points are computed, they lose their effectiveness in high-dimensions (typically about five dimensions).

A good MLAD platform doesn’t rely on traditional batch clustering such as k-means. It is feature agnostic, dimension agnostic and can deal with missing or additional dimensions (features in an event) on the fly, as they appear.

Adaptability and self-tuning: Over time, even the most persistent habits tend to change. Users may switch to other applications, move to new geographical locations, etc. A platform that is based on machine learning adapts over time to new patterns and user habits. Old unusual patterns become the new norm if they persist for a long enough period. All conditional event probabilities keep updating over time.

Since organizations tend to be very different in the usage profiles, cloud app mix, event dimensions, and number of users, it’s important to keep a separate model for each organization and let it shift over time based on that organization’s change over time.

Future-proofing: An MLAD platform is agnostic to the semantics of input features. All it cares about is the statistical probability of each feature to occur in its specific context. We can add features (think about installing a new security camera, or any other new sensor) without code changes to the platform. The moment a new event source is introduced as a new input is the moment that you can detect anomalies in it. In the coming months, we plan to enrich our data with more features that will enable us to introduce additional data flows and models into the Netskope MLAD platform.

future proof words written by 3d hand

Personalization: Good MLAD studies each source separately, yet all in parallel. In Netskope’s MLAD, a source can be anything: a user, device, department, etc. In the real world, different sources tend to be very different in their normal behavior. In our experience, this fine-grained study of each source separately greatly improves signal-to-noise ratios.

Scalability: The algorithm we use can process tens of thousands of events per second per each tenant/model thread on standard hardware. We can run hundreds of such threads in parallel and horizontally scale as we grow. We can analyze the probability of any event in near constant time versus all prior historical events. The time to calculate the probability of any event is linear with the number of dimensions in the event. We detect anomalies as they come in, at a speed that is small constant multiplier over plain I/O of the same data.

User-friendliness: Each anomalous event is dissected and explained in-context using “smoking gun” evidence. For example, we may say, “This event is highly unusual (1 in 9.67 million likelihood) because, for this particular user, the source location is unusual, and the time of day is unusual, and this application has never been used before.” We do this while contrasting rare and unusual events with normal or common patterns. We don’t pass judgment on the maliciousness of an event; we only focus on likelihoods based on historical evidence. It is up to the user, given the information they have (and we don’t) to decide whether to take action on the information our anomaly-detection platform provides.

Dog food: As we were developing and testing MLAD at Netskope, we came across several interesting revelations. Users were downloading sensitive files from one app and then re-uploading those files to a separate app. After taking a closer look, we found that sensitive may have been been exfiltrated;  file names included “Strategic Plan.pdf,” “passwords.txt” and “XYZ_litigation.docx.” This was one of the early indications that MLAD was kicking, and we were on the right track. Since then we’ve been discovering other unusual patterns that we had not anticipated before seeing MLAD in action.

“Solving security” is a tall order. Complex systems with many applications and users, and millions of possible access patterns can never be 100% secure. Our mission is to keep improving our tools. MLAD is one of these tools. We hope it will keep getting better and help our customers in their quest to keep their systems more secure.