The rising popularity of the microservice architectural style has led to a growing demand for automated testing approaches tailored to these systems. EvoMaster is a state-of-the-art tool that uses Evolutionary Algorithms (EAs) to automatically generate test cases for microservices’ REST APIs. One limitation of these EAs is the use of unit-level search heuristics, such as branch distances, which focus on fine-grained code coverage and may not effectively capture the complex, interconnected behaviors characteristic of system-level testing. To address this limitation, we propose a new search heuristic (MISH) that uses real-time automaton learning to guide the test case generation process. We capture the sequential call patterns exhibited by a test case by learning an automaton from the stream of log events outputted by different microservices within the same system. Therefore, MISH learns a representation of the system-wide behavior, allowing us to define the fitness of a test case based on the path it traverses within the inferred automaton. We empirically evaluate MISH’s effectiveness on six real-world benchmark microservice applications and compare it against a state-of-the-art technique, MOSA, for testing REST APIs. Our evaluation shows promising results for using MISH to guide the automated test case generation within EvoMaster.

We present the efficient implementations of probabilistic deterministic finite automaton learning methods available in FlexFringe. These implement well-known strategies for state-merging including several modifications to improve their performance in practice. We show experimentally that these algorithms obtain competitive results and significant improvements over a default implementation. We also demonstrate how to use FlexFringe to learn interpretable models from software logs and use these for anomaly detection. Although less interpretable, we show that learning smaller more convoluted models improves the performance of FlexFringe on anomaly detection, outperforming an existing solution based on neural nets.

In the context of the ever-evolving 5G landscape, where network management and control are paramount, a new Radio Access Network (RAN) as emerged. This innovative RAN offers a revolutionary approach by enabling the flexible distribution of baseband functions across various nodes, all tailored to meet the ever-shifting demands of both system requirements and user traffic patterns. As users move within the network, the need to anticipate and strategically position these baseband functions becomes crucial for seamless network operation. Traditionally, this challenge has been tackled through a two-step process: first, forecasting traffic patterns, and then optimizing resource allocation accordingly. However, this approach falls short in guaranteeing an efficient placement when actual traffic demands surge onto the network. It often leads to resource overbooking, constraint violations, and excessive power consumption, putting strain on the network’s capabilities. In this paper, we introduce a novel framework based on a black-box optimization approach. This tool empowers prediction algorithms not just with historical traffic data but also with insights from optimization outcomes. The goal is to minimize a loss function related to power consumption and constraint violation: this ensures a predicted placement that is feasible and whose power is close to optimal. This approach ensures that the predicted placement is both feasible and power-efficient, bridging the gap between theoretical prediction and practical implementation. Remarkably, our proposed method, while potentially sacrificing some degree of traffic prediction accuracy, outperforms the conventional two-step approach by delivering a more efficient baseband function placement.

Explainable Artificial Intelligence (XAI) aims to improve the transparency of machine learning (ML) pipelines. We systematize the increasingly growing (but fragmented) microcosm of studies that develop and utilize XAI methods for defensive and offensive cybersecurity tasks. We identify 3 cybersecurity stakeholders, i.e., model users, designers, and adversaries, who utilize XAI for 4 distinct objectives within an ML pipeline, namely 1) XAI-enabled user assistance, 2) XAI-enabled model verification, 3) explanation verification & robustness, and 4) offensive use of explanations. Our analysis of the literature indicates that many of the XAI applications are designed with little understanding of how they might be integrated into analyst workflows – user studies for explanation evaluation are conducted in only 14% of the cases. The security literature sometimes also fails to disentangle the role of the various stakeholders, e.g., by providing explanations to model users and designers while also exposing them to adversaries. Additionally, the role of model designers is particularly minimized in the security literature. To this end, we present an illustrative tutorial for model designers, demonstrating how XAI can help with model verification. We also discuss scenarios where interpretability by design may be a better alternative. The systematization and the tutorial enable us to challenge several assumptions, and present open problems that can help shape the future of XAI research within cybersecurity.

Interpretability of reinforcement learning policies is essential for many real-world tasks but learning such interpretable policies is a hard problem. Particularly, rule-based policies such as decision trees and rules lists are difficult to optimize due to their non-differentiability. While existing techniques can learn verifiable decision tree policies, there is no guarantee that the learners generate a policy that performs optimally. In this work, we study the optimization of size-limited decision trees for Markov Decision Processes (MPDs) and propose OMDTs: Optimal MDP Decision Trees. Given a user-defined size limit and MDP formulation, OMDT directly maximizes the expected discounted return for the decision tree using Mixed-Integer Linear Programming. By training optimal tree policies for different MDPs we empirically study the optimality gap for existing imitation learning techniques and find that they perform sub-optimally. We show that this is due to an inherent shortcoming of imitation learning, namely that complex policies cannot be represented using size-limited trees. In such cases, it is better to directly optimize the tree for expected return. While there is generally a trade-off between the performance and interpretability of machine learning models, we find that on small MDPs, depth 3 OMDTs often perform close to optimally.

This paper reports on the first international competition on AI for the traveling salesman problem (TSP) at the International Joint Conference on Artificial Intelligence 2021 (IJCAI-21). The TSP is one of the classical combinatorial optimization problems, with many variants inspired by real-world applications. This first competition asked the participants to develop algorithms to solve an orienteering problem with stochastic weights and time windows (OPSWTW). It focused on two learning approaches: surrogate-based optimization and deep reinforcement learning. In this paper, we describe the problem, the competition setup, and the winning methods, and give an overview of the results. The winning methods described in this work have advanced the state-of-the-art in using AI for stochastic routing problems. Overall, by organizing this competition we have introduced routing problems as an interesting problem setting for AI researchers. The simulator of the problem has been made open-source and can be used by other researchers as a benchmark for new learning-based methods. The instances and code for the competition are available at https://github.com/paulorocosta/ai-for-tsp-competition.

These days more companies are shifting towards using cloud environments to provide their services to their client. While it is easy to set up a cloud environment, it is equally important to monitor the system’s runtime behaviour and identify anomalous behaviours that occur during its operation. In recent years, the utilisation of Recurrent Neural Networks (RNNs) and Deep Neural Networks (DNNs) to detect anomalies that might occur during runtime has been a trending approach. However, it is unclear how to explain the decisions made by these networks and how these networks should be interpreted to understand the runtime behaviour that they model. On the contrary, state machine models provide an easier manner to interpret and understand the behaviour that they model. In this work, we propose an approach that learns state machine models to model the runtime behaviour of a cloud environment that runs multiple microservice applications. To the best of our knowledge, this is the first work that tries to apply state machine models to microservice architectures. The state machine model is used to detect the different types of attacks that we launch on the cloud environment. From our experiment results, our approach can detect the attacks very well, achieving a balanced accuracy of 99.2% and a F1 score of 0.982.

Decision trees are a popular choice of explainable model, but just like neural networks, they suffer from adversarial examples. Existing algorithms for fitting decision trees robust against adversarial examples are greedy heuristics and lack approximation guarantees. In this paper we propose ROCT, a collection of methods to train decision trees that are optimally robust against user-specified attack models. We show that the min-max optimization problem that arises in adversarial learning can be solved using a single minimization formulation for decision trees with 0-1 loss. We propose such formulations in Mixed-Integer Linear Programming and Maximum Satisfiability, which widely available solvers can optimize. We also present a method that determines the upper bound on adversarial accuracy for any model using bipartite matching. Our experimental results demonstrate that the existing heuristics achieve close to optimal scores while ROCT achieves state-of-the-art scores.

Ideal cyber threat intelligence (CTI) includes insights into attacker strategies that are specific to a network under observation. Such CTI currently requires extensive expert input for obtaining, assessing, and correlating system vulnerabilities into a graphical representation, often referred to as an attack graph (AG). Instead of deriving AGs based on system vulnerabilities, this work advocates the direct use of intrusion alerts. We propose SAGE, an explainable sequence learning pipeline that automatically constructs AGs from intrusion alerts without a priori expert knowledge. SAGE exploits the temporal and probabilistic dependence between alerts in a suffix-based probabilistic deterministic finite automaton (S-PDFA)-a model that brings infrequent severe alerts into the spotlight and summarizes paths leading to them. Attack graphs are extracted from the model on a per-victim, per-objective basis. SAGE is thoroughly evaluated on three open-source intrusion alert datasets collected through security testing competitions in order to analyze distributed multi-stage attacks. SAGE compresses over 330k alerts into 93 AGs that show how specific attacks transpired. The AGs are succinct, interpretable, and provide directly relevant insights into strategic differences and fingerprintable paths. They even show that attackers tend to follow shorter paths after they have discovered a longer one in 84.5% of the cases.

The 5G Radio Access Network (RAN) virtualization aims to improve network quality and lower the operator’s costs. One of its main features is the functional split, i.e., dividing the instantiation of RAN baseband functions into different units over metro-network nodes. However, its optimal placement is non-trivial: it depends on the application requirements and on the expected traffic volume, whose daily variation highly impacts the total power consumption. Current optimization solutions fail to provide a placement solution capable of handling traffic fluctuations. In fact, the standard machine learning algorithms used in the literature for planning the network resources in advance result in an allocation that is inadequate to carry the actual traffic at all the time-slots. Hence, we must reserve an artificial buffer capacity in the nodes to ensure feasibility. Instead, our proposed method exploits a fine-grained two-step multi-task algorithm that predicts the mean and quantile traffic, making the artificial capacity no longer necessary. The subsequent placement uses mixed-integer linear programming and a heuristic. The former considers the expected traffic in the objective function (to estimate costs) and the quantile in the constraints (to enforce capacity limits). The heuristic combines the mean and quantile results to minimize the power and comply with the requirements. While using sufficiently large artificial buffers guarantees robustness with a mild power increase compared to the oracle, the fine-grained multi-task model improves the results, reducing the power consumption compared to the mean and meets all constraints. The heuristic enables significant computational time reduction.

Attack graphs (AG) are a popular area of research that display all the paths an attacker can exploit to penetrate a network. Existing techniques for AG generation rely heavily on expert input regarding vulnerabilities and network topology. In this work, we advocate the use of AGs that are built directly using the actions observed through intrusion alerts, without prior expert input. We have developed an unsupervised visual analytics system, called SAGE, to learn alert-driven attack graphs. We show how these AGs (i) enable forensic analysis of prior attacks, and (ii) enable proactive defense by providing relevant threat intelligence regarding attacker strategies. We believe that alert-driven AGs can play a key role in AI-enabled cyber threat intelligence as they open up new avenues for attacker strategy analysis whilst reducing analyst workload.

Current state-of-the-art algorithms for training robust decision trees have high runtime costs and require hours to run. We present GROOT, an efficient algorithm for training robust decision trees and random forests that runs in a matter of seconds to minutes. Where before the worst-case Gini impurity was computed iteratively, we find that we can solve this function analytically to improve time complexity from O(n) to O(1) in terms of n samples. Our results on both single trees and ensembles on 14 structured datasets as well as on MNIST and Fashion-MNIST demonstrate that GROOT runs several orders of magnitude faster than the state-of-the-art works and also shows better performance in terms of adversarial accuracy on structured data.

Attack graphs (AG) are used to assess pathways availed by cyber adversaries to penetrate a network. State-of-the-art approaches for AG generation focus mostly on deriving dependencies between system vulnerabilities based on network scans and expert knowledge. In real-world operations however, it is costly and ineffective to rely on constant vulnerability scanning and expert-crafted AGs. We propose to automatically learn AGs based on actions observed through intrusion alerts, without prior expert knowledge. Specifically, we develop an unsupervised sequence learning system, SAGE, that leverages the temporal and probabilistic dependence between alerts in a suffix-based probabilistic deterministic finite automaton (S-PDFA) – a model that accentuates infrequent severe alerts and summarizes paths leading to them. AGs are then derived from the S-PDFA on a per-objective, per-victim basis. Tested with intrusion alerts collected through Collegiate Penetration Testing Competition, SAGE compresses over 330k alerts into 93 AGs. These AGs reflect the strategies used by the participating teams. The AGs are succinct, interpretable, and capture behavioral dynamics, e.g., that attackers will often follow shorter paths to re-exploit objectives.

Imitation learning provides a way to automatically construct a controller by mimicking human behavior from data. For safety-critical systems such as autonomous vehicles, it can be problematic to use controllers learned from data because they cannot be guaranteed to be collision-free. Recently, a method has been proposed for learning a multi-mode hybrid automaton cruise controller (MOHA). Besides being accurate, the logical nature of this model makes it suitable for formal verification. In this paper, we demonstrate this capability using the SpaceEx hybrid model checker as follows. We develop an automated tool to translate the automaton model into constraints and equations required by SpaceEx. We then verify that a pure MOHA controller is not collision-free. By adding a safety state based on headway in time, a rule that human drivers should follow anyway, we do obtain a provably safe cruise control. Moreover, the safe controller remains more humanlike than existing cruise controllers.

We provide a new formulation for the problem of learning the optimal classification tree of a given depth as a binary linear program. A limitation of previously proposed Mathematical Optimization formulations is that they create constraints and variables for every row in the training data. As a result, the running time of the existing Integer Linear programming (ILP) formulations increases dramatically with the size of data. In our new binary formulation, we aim to circumvent this problem by making the formulation size largely independent from the training data size. We show experimentally that our formulation achieves better performance than existing formulations on both small and large problem instances within shorter running time.

This paper proposes a novel hybrid model for learning discrete and continuous dynamics of car-following behaviors. Multiple modes representing driving patterns are identified by partitioning the model into groups of states. The model is visualizable and interpretable for car-following behavior recognition, traffic simulation, and human-like cruise control. The experimental results using the next generation simulation datasets demonstrate its superior fitting accuracy over conventional models.

Industrial Control Systems (ICS) such as water and power are critical to any society. Process anomaly detection mechanisms have been proposed to protect such systems to minimize the risk of damage or loss of resources. In this paper, a graphical model-based approach is proposed for profiling normal operational behavior of an operational ICS referred to as SWaT (Secure Water Treatment). Timed automata are learned as a model of regular behaviors shown in sensors signal like fluctuations of water level in tanks. Bayesian networks are learned to discover dependencies between sensors and actuators. The models are used as a one-class classifier for process anomaly detection, recognizing irregular behavioral patterns and dependencies. The detection results can be interpreted and the abnormal sensors or actuators localized due to the interpretability of the graphical models. This approach is applied to a dataset collected from SWaT. Experimental results demonstrate the model's superior performance on both precision and run-time over methods including support vector machine and deep neural networks. The underlying idea is generic and applicable to other industrial control systems such as power and transportation.

A popular method in machine learning for supervised classification is a decision tree. In this work we propose a new framework to learn fuzzy decision trees using mathematical programming. More specifically, we encode the problem of constructing fuzzy decision trees using a Mixed Integer Linear Programming (MIP) model, which can be solved by any optimization solver. We compare the performance of our method with the performance of off-the-shelf decision tree algorithm CART and Fuzzy Inference Systems (FIS) using benchmark data-sets. Our initial results are promising and show the advantages of using non-crisp boundaries for improving classification accuracy on testing data.

Finite state models, such as Mealy machines or state charts, are often used to express and specify protocol and software behavior. Consequently, these models are often used in verification, testing, and for assistance in the development and maintenance process. Reverse engineering these models from execution traces and log files, in turn, can accelerate and improve the software development and inform domain experts about the processes actually executed in a system. We present name, an open-source software tool to learn variants of finite state automata from traces using a state-of-the-art evidence-driven state-merging algorithm at its core. We embrace the need for customized models and tailored learning heuristics in different application domains by providing a flexible, extensible interface.

Passive learning techniques infer graph models on the behavior of a system from large trace logs. The research community has been dedicating great effort in making passive learning techniques more scalable and ready to use by industry. However, there is still a lack of empirical knowledge on the usefulness and applicability of such techniques in large scale real systems. To that aim, we conducted action research over nine months in a large payment company. Throughout this period, we iteratively applied passive learning techniques with the goal of revealing useful information to the development team. In each iteration, we discussed the findings and challenges to the expert developer of the company, and we improved our tools accordingly. In this paper, we present evidence that passive learning can indeed support development teams, a set of lessons we learned during our experience, a proposed guide to facilitate its adoption, and current research challenges.

We present a novel way to detect infected hosts and identify malware in networks by analyzing network communication statistics with state-of-the-art automata learning algorithms. The automata encode patterns of short-term interactions in known malicious hosts, and are used to obtain small but effective fingerprints of machine behavior. We showcase the effectiveness of our system, named BASTA1(Behavioral Analytics System using Timed Automata), on a public dataset containing Netflow traces of real-world botnet malware. Compared to a deep packet inspection of communication content, Netflows are easy and cheap to collect and analyze, and preserve a greater degree of privacy. Even though the high level of abstraction in Netflow data makes it more difficult to utilize it, BASTA shows very impressive results achieving high accuracy in several settings while returning few false positives. It is also capable of detecting infections of previously unseen malware.

Machine learning has become one of the go-to methods for solving problems in the field of networking. This development is driven by data availability in large-scale networks and the commodification of machine learning frameworks. While this makes it easier for researchers to implement and deploy machine learning solutions on networks quickly, there are a number of vital factors to account for when using machine learning as an approach to a problem in networking and translate testing performance to real networks deployments successfully. This paper, rather than presenting a particular technical result, discusses the necessary considerations to obtain good results when using machine learning to analyze network-related data.

We consider dynamic group services, where outputs based on small samples of privacy-sensitive user inputs are repetitively computed. The leakage of user input data is analysed, caused by producing multiple outputs, resulting from inputs of frequently changing sets of users. A cryptographic technique, known as random user selection, is investigated. We show the effect of random user selection, given different types of output functions, thereby disproving earlier work. A new security measure is introduced, which provably improves the privacy-preserving effect of random user selection, irrespective of the output function. We show how this new security measure can be implemented in existing cryptographic protocols. To investigate the effectiveness of our security measure, we conducted a couple of statistical simulations with large user populations, which show that it forms a key ingredient, at least for the output function addition. Without it, an adversary is able to determine a user input, with increasing accuracy when more outputs become available. When the security measure is implemented, an adversary remains oblivious of user inputs, even when thousands of outputs are collected. Therefore, our new security measure assures that random user selection is an effective way of protecting the privacy of dynamic group services.

Automated network traffic analysis using machine learning techniques plays an important role in managing networks and IT infrastructure. A key challenge to the correct and effective application of machine learning is dealing with non-stationary learning data sources and concept drift. Traffic evolves overtime due to new technology, software, services being used, changes in user behavior but also due to changes in network graphs like dynamic IP address assignment. In this paper, we present an automatic online method to detect change-points in network traffic based on IP flow record analysis. This technique is used to segment an observed behavior into smaller consecutive behaviors differing one from another. The segmented traffic is used to learn small communication profile characterizing accurately the activities present between two observed change-points. We validate our method using synthetic data and outline a real-world application to botnet hosts behavior modeling.

The task of network traffic monitoring has evolved drastically with the ever-increasing amount of data flowing in large scale networks. The automated analysis of this tremendous source of information often comes with using simpler models on aggregated data (e.g. IP flow records) due to time and space constraints. A step towards utilizing IP flow records more effectively are stream learning techniques. We propose a method to collect a limited yet relevant amount of data in order to learn a class of complex models, finite state machines, in real-time. These machines are used as communication profiles to fingerprint, identify or classify hosts and services and offer high detection rates while requiring less training data and thus being faster to compute than simple models.

Abstract This paper provides a gentle introduction to problem-solving with the IDP3 system. The core of IDP3 is a finite model generator that supports first-order logic enriched with types, inductive definitions, aggregates and partial functions. It offers its users a modeling language that is a slight extension of predicate logic and allows them to solve a wide range of search problems. Apart from a small introductory example, applications are selected from problems that arose within machine learning and data mining research. These research areas have recently shown a strong interest in declarative modeling and constraint-solving as opposed to algorithmic approaches. The paper illustrates that the IDP3 system can be a valuable tool for researchers with such an interest. The first problem is in the domain of stemmatology, a domain of philology concerned with the relationship between surviving variant versions of text. The second problem is about a somewhat related problem within biology where phylogenetic trees are used to represent the evolution of species. The third and final problem concerns the classical problem of learning a minimal automaton consistent with a given set of strings. For this last problem, we show that the performance of our solution comes very close to that of the state-of-the art solution. For each of these applications, we analyze the problem, illustrate the development of a logic-based model and explore how alternatives can affect the performance.

Intraspecific studies often make use of haplotype networks instead of gene genealogies to represent the evolution of a set of genes. Cassens et al. proposed one such network reconstruction method, based on the global maximum parsimony principle, which was later recast by the first author of the present work as the problem of finding a minimum common supergraph of a set of t partially labelled trees. Although algorithms have been proposed for solving that problem on two graphs, the complexity of the general problem on trees remains unknown. In this paper, we show that the corresponding decision problem is NP-complete for t=3. We then propose a declarative programming approach to solving the problem to optimality in practice, as well as a heuristic approach, both based on the idpsystem, and assess the performance of both methods on randomly generated data.

The availability of real-life data sets is of crucial importance for algorithm and application development, as these often require insight into the specific properties of the data. Often, however, such data are not released because of their proprietary and confidential nature. We propose to solve this problem using the statistical technique of multiple imputation, which is used as a powerful method for generating realistic synthetic data sets. Additionally, it is shown how the generated records can be combined into networked data using clustering techniques.

We develop a novel learning algorithm RTI for identifying a deterministic real-time automaton (DRTA) from labeled time-stamped event sequences. The RTI algorithm is based on the current state of the art in deterministic finite-state automaton (DFA) identification, called evidence-driven state-merging (EDSM). In addition to having a DFA structure, a DRTA contains time constraints between occurrences of consecutive events. Although this seems a small difference, we show that the problem of identifying a DRTA is much more difficult than the problem of identifying a DFA: identifying only the time constraints of a DRTA given its DFA structure is already NP-complete. In spite of this additional complexity, we show that RTI is a correct and complete algorithm that converges efficiently (from polynomial time and data) to the correct DRTA in the limit. To the best of our knowledge, this is the first algorithm that can identify a timed automaton model from time-stamped event sequences.A straightforward alternative to identifying DRTAs is to identify a DFA that models time implicitly, i.e., a DFA that uses different states for different points in time. Such a DFA can be identified by first sampling the timed sequences using a fixed frequency, and subsequently applying EDSM to the resulting non-timed event sequences. We evaluate the performance of both RTI and this sampling approach experimentally on artificially generated data. In these experiments RTI outperforms the sampling approach significantly. Thus, we show that if we obtain data from a real-time system, it is easier to identify a DRTA from this data than to identify an equivalent DFA.

We advocate the use of an explicit time representation in syntactic pattern recognition because it can result in more succinct models and easier learning problems. We apply this approach to the real-world problem of learning models for the driving behavior of truck drivers. We discretize the values of onboard sensors into simple events. Instead of the common syntactic pattern recognition approach of sampling the signal values at a fixed rate, we model the time constraints using timed models. We learn these models using the RTI+ algorithm from grammatical inference, and show how to use computational mechanics and a form of semi-supervised classification to construct a real-time automaton classifier for driving behavior. Promising results are shown using this new approach.

In this paper, we investigate how to modify the naive Bayes classifier in order to perform classification that is restricted to be independent with respect to a given sensitive attribute. Such independency restrictions occur naturally when the decision process leading to the labels in the data-set was biased; e.g., due to gender or racial discrimination. This setting is motivated by many cases in which there exist laws that disallow a decision that is partly based on discrimination. Naive application of machine learning techniques would result in huge fines for companies. We present three approaches for making the naive Bayes classifier discrimination-free: (i) modifying the probability of the decision being positive, (ii) training one model for every sensitive attribute value and balancing them, and (iii) adding a latent variable to the Bayesian model that represents the unbiased label and optimizing the model parameters for likelihood using expectation maximization. We present experiments for the three approaches on both artificial and real-life data.