Understanding the Relationship Between AI and Cybersecurity

The first thing many of us think about when it comes to the future relationship between artificial intelligence (AI) and cybersecurity is Skynet—the fictional neural net-based group mind from the “Terminator” movie franchise. But at least one security professional (with a somewhat rosier view) suggested that AI must be understood across a broader landscape, regarding how it will influence cybersecurity and how IT can use AI to plan for future security technology purchases.

March Madness 2018: Bracket Predictions, Odds for Thursday’s Sweet 16 Schedule

Clayton Custer is hoping to lead Loyola to another NCAA tournament victory.Associated Press

The first weekend of the NCAA tournament was filled with upsets and buzzer-beating finishes.

20 Critical Security Controls: Control 18 – Application Software Security

Today, I will be going over Control 18 from version 7 of the CIS top 20 Critical Security Controls – Application Software Security. I will go through the eleven requirements and offer my thoughts on what I’ve found.

Researchers Can Earn up to $15K in Netflix’s New Public Bug Bounty Program

Netflix has launched a public bug bounty program through which security researchers can receive rewards of up to $15,000.

Ndamukong Suh Should Be NFL’s Most Coveted Free Agent Left on the Market

Tom Szczerbowski/Getty Images

Eight years into his NFL career, Ndamukong Suh remains equal parts dominant and maddening. He’s also the best player left in the 2018 free-agent market. 

Cowboys’ Window of Opportunity Being Slammed Shut by Front Office Foul-Ups

Michael Perez/Associated Press

A franchise quarterback playing under his rookie contract is the NFL‘s most precious commodity. He’s a one-man solution to the two biggest problems facing every team: how to acquire a franchise quarterback (he’s already here!) and how to build around him (he’s on a cheap deal, so we can pay other guys!

[SANS ISC] Automatic Hunting for Malicious Files Crossing your Network

I published the following diary on isc.sans.org: “Automatic Hunting for Malicious Files Crossing your Network“:

How to stop Facebook from sharing your data with friend’s apps – CNET

How many clicks does it take to keep your Facebook data private?

Ansarada gets $18M in Series A funding to help companies better prepare for major deals

Australian startup Ansarada, which provides tools for companies preparing for a major transaction, will expand in the United States, Europe, the Middle East and Africa after raising an $18 million Series A. The funding was led by Ellerston Capital, with participation from Tempus Partners, Belay Capital and Australian Ethical Investments. A noteworthy detail about the raise is that all advisory fees from the deal will be donated to Ugandan and Nepalese charities through Ansarada’s partnership with Adara Partners, a corporate advisory firm made up of financial services experts who donate their fees to help women and children living in poverty.

Travel site Orbitz warns data breach may have exposed 880,000 payment card details

Online travel services firm Orbitz has revealed that it has suffered a “data security incident” which may have compromised the sensitive information of hundreds of thousands of customers.According to Orbitz, which was acquired by Expedia in two years ago, hackers were able to infiltrate a legacy version of the company’s travel booking platform between October 1, 2017 and December 22, 2017. The unauthorised intruders may have accessed the personal data of approximately 880,000 customers, including the following information:customers’ payment card detailscustomers’ full namescustomers’ dates of birthcustomers’ gendercustomers’ email addressescustomers’ physical addressescustomers’ billing addressescustomers’ phone numbersThe data is said to be related to purchases made in the first six months of 2016 for Orbitz platform customers, and between January 1 2016 and December 22 2017 for “certain partners’ customers.”This exposure for almost two years of the customers of Orbitz’s business partners is an important point.It’s very possible that your company, for instance, books your travel through a service like Amex Global Business Travel, and as a consequence may not realise that Amex was relying upon Orbitz’s services.

Interpreting predictive models with Skater: Unboxing model opacity

Over the years, machine learning (ML) has come a long way, from its existence as experimental research in a purely academic setting to wide industry adoption as a means for automating solutions to real-world problems. But oftentimes, these algorithms are still perceived as alchemy because of the lack of understanding of the inner workings of these model (see Ali Rahimi, NIPS ’17). There is often a need to verify the reasoning of such ML systems to hold algorithms accountable for the decisions predicted. Researchers and practitioners are grappling with the ethics of relying on predictive models that might have unanticipated effects on human life, such as the algorithms evaluating eligibility for mortgage loans or powering self-driving cars (see Kate Crawford, NIPS ’17, “The Trouble with Bias”). Data Scientist Cathy O’Neil has recently written an entire book filled with examples of poor interpretability as a dire warning of the potential social carnage from misunderstood models—e.g., modeling bias in criminal sentencing or using dummy features with human bias while building financial models.

There is also a trade off in balancing a model’s interpretability and its performance. Practitioners often choose linear models over complex ones, compromising performance for interpretability, which might be fine for many use cases where the cost of an incorrect prediction is not high. But, in some scenarios, such as credit scoring or the judicial system, models have to be both highly accurate and understandable. In fact, the ability to account for the fairness and transparency of these predictive models has been mandated for legal compliance.

At DataScience.com, where I’m a lead data scientist, we feel passionately about the ability of practitioners to use models to ensure safety, non-discrimination, and transparency. We recognize the need for human interpretability, and we recently open sourced a Python framework called Skater as an initial step to enable interpretability for researchers and applied practitioners in the field of data science.

Model evaluation is a complex problem, so I will segment this discussion into two parts. In this first piece, I will dive into model interpretation as a theoretical concept and provide a high-level overview of Skater. In the second part, I will share a more detailed explanation on the algorithms Skater currently supports, as well as the library’s feature roadmap.

What is model interpretation?

The concept of model interpretability in the field of machine learning is still new, largely subjective, and, at times, controversial (see Yann LeCun’s response to Ali Rahimi’s talk). Model interpretation is the ability to explain and validate the decisions of a predictive model to enable fairness, accountability, and transparency in the algorithmic decision-making (for a more detailed explanation on the definition of transparency in machine learning, see “Challenges of Transparency” by Adrian Weller). Or, to state it formally, model interpretation can be defined as the ability to better understand the decision policies of a machine-learned response function to explain the relationship between independent (input) and dependent (target) variables, preferably in a human interpretable way.

Ideally, you should be able to query the model to understand the what, why, and how of its algorithmic decisions

  • What information can the model provide to avoid prediction errors? You should be able to query and understand latent variable interactions in order to evaluate and understand, in a timely manner, what features are driving predictions. This will ensure the fairness of the model.
  • Why did the model behave in a certain way? You should be able to identify and validate the relevant variables driving the model’s outputs. Doing so will allow you to trust in the reliability of the predictive system, even in unforeseen circumstances. This diagnosis will ensure accountability and safety of the model.
  • How can we trust the predictions made by the model? You should be able to validate any given data point to demonstrate to business stakeholders and peers that the model works as expected. This will ensure transparency of the model.

Existing techniques capturing model interpretation

The idea of model interpretation is to achieve a better understanding of the mathematical model—which most likely could be achieved by developing a better understanding of the features contributing to the model. This form of understanding could possibly be enabled using popular data exploration and visualization approaches, like hierarchical clustering and dimensionality reduction techniques. Further evaluation and validation of models could be enabled using algorithms for model comparison for classification and regression using model specific scorers—AUC-ROC (area under the receiver operating curve) and MAE (mean absolute error). Let’s quickly touch on a few of those.

Exploratory data analysis and visualization

Exploratory data analysis can give one a better understanding of your data, in turn providing the expertise necessary to build a better predictive model. During the model-building process, achieving interpretability could mean exploring the data set in order to visualize and understand its “meaningful” internal structure and extract intuitive features with strong signals in a human interpretable way. This might become even more useful for unsupervised learning problems. Let’s go over a few popular data exploration techniques that could fall into the model interpretation category.

In this article, we will focus on model interpretation in regard to supervised learning problems.

B. model comparison and performance evaluation

In addition to data exploration techniques, model interpretation in a naive form could possibly be achieved using model evaluation techniques. Analysts and data scientists can possibly use model comparison and evaluation methods to assess the accuracy of the models. For example, with cross validation and evaluation metrics for classification and regression, you can measure the performance of a predictive model. You can optimize on the hyperparameters of the model balancing between bias and variance (see “Understanding the Bias-Variance Tradeoff“).

  • Classification: for example, F1-scores, AUC-ROC, brier-score, etc. Consider Figure 3, which shows how AUC-ROC can help measure the model performance on a multi-class problem on the popular iris data set. ROC AUC is a widely popular metric that helps in balancing between true positive rate (TPR) and false positive rate (FPR). It’s pretty robust in handling class imbalances as well. As shown in Figure 3, a ROC AUC (class-2) of 86% means that the probability of the trained classifier assigning a higher score to a positive example (belonging to class-2) than to a negative example (not belonging to class-2) is about 86%. Such aggregated performance metric might be helpful in articulating the global performance of a model. However, it fails to give detailed information on the reasons for misclassification if an error occurs—why did an example belonging to Class 0 get classified as Class 2 and an example belonging to Class 2 get classified as Class 1? Keep in mind, each misclassification may have a varying potential business impact.
  • Regression: for example, r-squared score (coefficient of determination), mean squared error, etc.

    Why the motivation for better model interpretation?

    The above mentioned data exploration and point estimates computed using evaluation techniques might be sufficient in measuring the overall performance of a sample data set if the predictive model’s objective function aligns (the loss function one is trying to optimize) with the business metric (the one closely tied to your real-world goal), and the data set used for training is stationary. However, in real-world scenarios, that is rarely the case, and capturing model performance using point estimates is not sufficient. For example, an intrusion detection system (IDS), a cyber-security application, is prone to evasion attacks where an attacker may use adversarial inputs to beat the secure system (note: adversarial inputs are examples that are intentionally engineered by an attacker to trick the machine learning model to make false predictions). The model’s objective function in such cases may act as a weak surrogate to the real-world objectives. A better interpretation might be needed to identify the blind spots in the algorithms to build a secure and safe model by fixing the training data set prone to adversarial attacks (for further reading, see Moosavi-Dezfooli, et al., 2016, DeepFool and Goodfellow, et al., 2015, Explaining and harnessing adversarial examples).

    Moreover, a model’s performance plateaus over time when trained on a static data set (not accounting for the variability in the new data). For example, the existing feature space may have changed after a model is operationalized in the wild or new information gets added into the training data set, introducing new unobserved associations, meaning that simply re-training a model will not be sufficient to improve the model’s prediction. Better forms of interpretations are needed to effectively debug the model to understand the algorithm behavior or to incorporate the new associations and interactions in the data set.

    There might also be a use case where the model’s prediction natively is correct—where the model’s prediction is as expected—but it ethically fails to justify its decision in a social setting because of data biasedness (e.g., “Just because I like Kurosawa does not mean I want to watch 3 Ninjas”). At this point in time, a more rigorous and transparent diagnosis of the inner working of the algorithm might be needed to build a more effective model.

    Even if one disagrees with all the above mentioned reasons as motivating factors for better interpretability needs, the traditional forms of model evaluation need a sound theoretical understanding of the algorithms or properties of statistical testing. It might be difficult for non-experts to grasp such details about the algorithm, often resulting in the failure of data-driven initiatives. A human interpretable interpretation(HII) of the model’s decision policies may provide insightful information that could easily be shared among peers (analysts, managers, data scientists, data engineers).

    Using such forms of explanations, which could be explained based on inputs and outputs, might help facilitate better communication and collaboration, enabling businesses to make more confident decisions (e.g., risk assessment/audit risk analysis in financial institutions). To reiterate, we define model interpretation as being able to account for fairness (unbiasedness/non-discriminative), accountability (reliable results), and transparency (being able to query and validate predictive decisions) of a predictive model—currently in regard to supervised learning problems.

    Dichotomy between Performance and Interpretability

    There seems to be a fundamental trade-off between performance and algorithm interpretability. Practitioners often settle with easier interpretable models—simple linear, logistic regression, decision trees—because they are much easier to validate and explain. One is able to trust a model if one can understand its inner working or its decision policies. But, as one is trying to apply these predictive models to solve real-world problems with access to high-dimensional heterogeneous complex data sets—automating the process of credit applications, detecting fraud, or predicting lifetime value of a customer—interpretable models often fall short in terms of performance. As practitioners try to improve the performance (i.e., accuracy) of the model using more complex algorithms, they struggle to strike a balance between performance and interpretability.

    Let’s look at the problem of balancing performance and interpretability with an example. Consider the above Figure 5. Let’s assume one is building a model to predict the loan approval for a certain group of customers. Linear models (e.g., linear classifiers like logistic regression with log-loss or ordinary least square (OLS) for regression) are simpler to interpret because the relationship between the input variables and the model’s output could be quantified in magnitude and direction using the model’s coefficient weights. This line of thought works fine if the decision boundary is monotonically increasing or decreasing. However, this is rarely the case with real-world data. Hence, the perplexity in balancing between the model’s performance and interpretability.

    In order to capture the non-monotonic relationship between the independent variable and the model’s response function, one generally has to make use of more complex models: ensembles, a random forest with a large number of decision trees, or a neural network with multiple hidden layers. The complexity increases further with text (Explaining Predictions of Non-Linear Classifiers in NLP using layer-wise relevance propagation (LRP)), computer vision (Ning et.al, NIPS’17, Relating Input Concepts to Convolutional Neural Network Decisions), and speech-based models with the need for human interpretability. For example, understanding of language-based models still remains a tough problem because of the ambiguity and uncertainty on the usage of similar words. Enabling human interpretability to understand such ambiguity in language models is useful in building use-case specific rules to understand, verify, and improve a model’s decision.

    Introducing Skater

    At Datascience.com, we have experienced interpretability challenges ourselves across different analytical use cases and projects, and understand the need for better model interpretation—preferably human interpretable interpretation (HII) expressed as inputs variables and model outputs (easily understood by non-experts). I specifically remember a project where we were building an ML model for summarizing consumer reviews. We wanted to capture the consumer sentiments (as positive or negative) as well as the specific reasons for each sentiment. Being time constrained, we thought it might be worth using an off-the-shelf model for sentiment analysis. We looked into many ML marketplace offerings, but we couldn’t decide on one to use because of trust issues and felt the need for better ways to interpret, verify, and validate models.

    As we looked around, we couldn’t find a mature open source library that consistently enabled global (on the basis of a complete data set) and local (on the basis of an individual prediction) interpretation, so we developed a library from the ground up called Skater (see Figure 6).

    Skater is a Python library designed with the goal to demystify the inner workings of any type of predictive model that is language and framework agnostic. Currently, it supports algorithms to enable interpretability with regard to supervised learning problems.

    The interpretation algorithms currently supported are post-hoc in nature. As in, while Skater provides a post-hoc mechanism to evaluate and verify the inner workings of the predictive models based on independent (input) and dependent (target) variables, it does not support ways to build interpretable models (e.g., Rule Ensembles, Friedman, Bayesian Rule List).

    This approach helps us to apply interpretability to machine learning systems depending on the analytical use cases—post-hoc operation could be expensive, and extensive interpretability may not be needed all the time. The library has embraced object-oriented and functional programming paradigms as deemed necessary to provide scalability and concurrency while keeping code brevity in mind. A high-level overview of such an interpretable system is shown in Figure 7.

    Using Skater for model interpretation

    Note: the complete code for the inline examples are added as reference links to the figures below.

    With Skater one can:

    • Evaluate the behavior of a model on a complete data set or on a single prediction: Skater allows model interpretation both globally and locally by leveraging and improving upon a combination of existing techniques. For global explanations, Skater currently makes use of model-agnostic variable importance and partial dependence plots to judge the bias of a model and understand its general behavior. To validate a model’s decision policies for a single prediction, the library embraces a novel technique called local interpretable model agnostic explanation (LIME), which uses local surrogate models to assess performance (here are more details on LIME). Other algorithms are currently under development.

    from skater.core.explanations import Interpretation from skater.model import InMemoryModel ... eclf = VotingClassifier(estimators=[('lr', clf1), ('rf', clf2), ('gnb', clf3)], voting='soft') ... models = {'lr':clf1, 'rf':clf2, 'gnb':clf3, 'ensemble':eclf} interpreter = Interpretation(X_test, feature_names=data.feature_names) Global interpretation with model agnostic feature importance for model_key in models: pyint_model = InMemoryModel(models[model_key].predict_proba, examples=X_test) ax = ax_dict[model_key] interpreter.feature_importance.plot_feature_importance(pyint_model, ascending=False, ax=ax) ax.set_title(model_key)

The Digital Disconnect: 70% of UK employees not equipped with necessary tools and training

Sungard Availability Services ® (Sungard AS), a leading provider of information availability through managed IT, cloud and recovery services, today reveals that the skills shortage is having a detrimental impact on UK businesses and could pose serious risks in the years ahead. Both IT Decision Makers (31%), and Line of Business Decision Makers (41%) have labelled it as their biggest issue impacting digital initiatives, with seven in ten employees claiming they’re not getting the training or tools they need to add value back to the business.

The Key Challenges of Migrating Databases to the Cloud

By Roberto Mircoli, EMEA CTO for Virtustream 

As enterprises continue to embark on their digital transformation journeys part of this change may involve migrating in-house applications, databases and data to the cloud.  But while all the benefits of cloud are widely understood, migrating a database or an application to the cloud is not always smooth sailing and there can be challenges to overcome when transitioning.  Here I wanted to highlight some of the steps enterprises should take to ensure their database migration is successful.

Stop Lying About Quitting Facebook, All Your Data Are Belong To Us (Forbes)

(AP Photo/Marcio Jose Sanchez, File)

On Facebook , yesterday, there was a comment on a post about the recent “betrayal” by Facebook where it concerns our “private” data. The comment was simply the hashtag #deletefacebook. Posted, with apparently little irony, on Facebook. It’s an interesting juxtaposition of the current mess that Facebook finds itself in with its users. Perhaps I’m a day or ten years too late on this (not really, I’ve literally written about it numerous times), but it appears we need to have another conversation about the actual service Facebook provides and what about your data that is considered private.

880,000 payment cards affected in travel company data breach

by

Travel booking website Orbitz says that a data breach has affected 880,000 payment cards.

Inside Bezos’ private unconference, Mars

PALM SPRINGS, Calif. — “I get invited to everything, and everywhere I go, everyone wishes they had my job. But that’s not true here,” said Pablos Holman, a self-described futurist and inventor who has worked on lasers that kill mosquitoes and machines that suppress hurricanes.