arXiv subjects

Tansu Alpcan

Publications and source records attributed to Tansu Alpcan.

At least 37 records · Page 2Linked to original sources

arXiv2022

Adversarial Decisions on Complex Dynamical Systems using Game Theory

We apply computational Game Theory to a unification of physics-based models that represent decision-making across a number of agents within both cooperative and competitive processes. Here the competitors try to both positively influence their own returns, while negatively affecting those of their competitors. Modelling these interactions with the so-called Boyd-Kuramoto-Lanchester (BKL) complex dynamical system model yields results that can be applied to business, gaming and security contexts. This paper studies a class of decision problems on the BKL model, where a large set of coupled, switching dynamical systems are analysed using game-theoretic methods. Due to their size, the computational cost of solving these BKL games becomes the dominant factor in the solution process. To resolve this, we introduce a novel Nash Dominant solver, which is both numerically efficient and exact. The performance of this new solution technique is compared to traditional exact solvers, which traverse the entire game tree, as well as to approximate solvers such as Myopic and Monte Carlo Tree Search (MCTS). These techniques are assessed, and used to gain insights into both nonlinear dynamical systems and strategic decision making in adversarial environments.

cs.GT↗

arXiv2022

Achieving AI-enabled Robust End-to-End Quality of Experience over Radio Access Networks

Emerging applications such as Augmented Reality, the Internet of Vehicles and Remote Surgery require both computing and networking functions working in harmony. The End-to-end (E2E) quality of experience (QoE) for these applications depends on the synchronous allocation of networking and computing resources. However, the relationship between the resources and the E2E QoE outcomes is typically stochastic and non-linear. In order to make efficient resource allocation decisions, it is essential to model these relationships. This article presents a novel machine-learning based approach to learn these relationships and concurrently orchestrate both resources for this purpose. The machine learning models further help make robust allocation decisions regarding stochastic variations and simplify robust optimization to a conventional constrained optimization. When resources are insufficient to accommodate all application requirements, our framework supports executing some of the applications with minimal degradation (graceful degradation) of E2E QoE. We also show how we can implement the learning and optimization methods in a distributed fashion by the Software-Defined Network (SDN) and Kubernetes technologies. Our results show that deep learning-based modelling achieves E2E QoE with approximately 99.8\% accuracy, and our robust joint-optimization technique allocates resources efficiently when compared to existing differential services alternatives.

cs.NI↗

arXiv2022

Online Slice Reconfiguration for End-to-End QoE in 6G Applications

End-to-end (E2E) quality of experience (QoE) for 6G applications depends on the synchronous allocation of networking and computing resources, also known as slicing. However, the relationship between the resources and the E2E QoE outcomes is typically stochastic and non-stationary. Existing works consider known resource demands for slicing and formulate optimization problems for slice reconfiguration. In this work, we create and manage slices by learning the relationship between E2E QoE and resources. We develop a gradient-based online slice reconfiguration algorithm (OSRA) to reconfigure and manage slices in resource-constrained scenarios for radio access networks (RAN). We observe that our methodology meets the QoE requirements with high accuracy compared to existing approaches. It improves upon the existing approaches by approximately 98\% for bursty traffic variations. Our algorithm has fast convergence and achieves low E2E delay violations for lower priority slices.

cs.NI↗

arXiv2021

A Game-Theoretic Approach for AI-based Botnet Attack Defence

The new generation of botnets leverages Artificial Intelligent (AI) techniques to conceal the identity of botmasters and the attack intention to avoid detection. Unfortunately, there has not been an existing assessment tool capable of evaluating the effectiveness of existing defense strategies against this kind of AI-based botnet attack. In this paper, we propose a sequential game theory model that is capable to analyse the details of the potential strategies botnet attackers and defenders could use to reach Nash Equilibrium (NE). The utility function is computed under the assumption when the attacker launches the maximum number of DDoS attacks with the minimum attack cost while the defender utilises the maximum number of defense strategies with the minimum defense cost. We conduct a numerical analysis based on a various number of defense strategies involved on different (simulated) cloud-band sizes in relation to different attack success rate values. Our experimental results confirm that the success of defense highly depends on the number of defense strategies used according to careful evaluation of attack rates.

cs.CR↗

arXiv2021

A Communication Security Game on Switched Systems for Autonomous Vehicle Platoons

Vehicle-to-vehicle communication enables autonomous platoons to boost traffic efficiency and safety, while ensuring string stability with a constant spacing policy. However, communication-based controllers are susceptible to a range of cyber-attacks. In this paper, we propose a distributed attack mitigation defense framework with a dual-mode control system reconfiguration scheme to prevent a compromised platoon member from causing collisions via message falsification attacks. In particular, we model it as a switched system consisting of a communication-based cooperative controller and a sensor-based local controller and derive conditions to achieve global uniform exponential stability (GUES) as well as string stability in the sense of platoon operation. The switching decision comes from game-theoretic analysis of the attacker and the defender's interactions. In this framework, the attacker acts as a leader that chooses whether to engage in malicious activities and the defender decides which control system to deploy with the help of an anomaly detector. Imperfect detection reports associate the game with imperfect information. A dedicated state constraint further enhances safety against bounded but aggressive message modifications in which a bounded solution may still violate practical constraint e.g. vehicles nearly crashing. Our formulation uniquely combines switched systems with security games to strategically improve the safety of such autonomous vehicle systems.

cs.GT↗

arXiv2021

Local Intrinsic Dimensionality Signals Adversarial Perturbations

The vulnerability of machine learning models to adversarial perturbations has motivated a significant amount of research under the broad umbrella of adversarial machine learning. Sophisticated attacks may cause learning algorithms to learn decision functions or make decisions with poor predictive performance. In this context, there is a growing body of literature that uses local intrinsic dimensionality (LID), a local metric that describes the minimum number of latent variables required to describe each data point, for detecting adversarial samples and subsequently mitigating their effects. The research to date has tended to focus on using LID as a practical defence method often without fully explaining why LID can detect adversarial samples. In this paper, we derive a lower-bound and an upper-bound for the LID value of a perturbed data point and demonstrate that the bounds, in particular the lower-bound, has a positive correlation with the magnitude of the perturbation. Hence, we demonstrate that data points that are perturbed by a large amount would have large LID values compared to unperturbed samples, thus justifying its use in the prior literature. Furthermore, our empirical validation demonstrates the validity of the bounds on benchmark datasets.

cs.LG↗

arXiv2021

Achieving QoS for Real-Time Bursty Applications over Passive Optical Networks

Emerging real-time applications such as those classified under ultra-reliable low latency (uRLLC) generate bursty traffic and have strict Quality of Service (QoS) requirements. Passive Optical Network (PON) is a popular access network technology, which is envisioned to handle such applications at the access segment of the network. However, the existing standards cannot handle strict QoS constraints. The available solutions rely on instantaneous heuristic decisions and maintain QoS constraints (mostly bandwidth) in an average sense. Existing works with optimal strategies are computationally complex and are not suitable for uRLLC applications. This paper presents a novel computationally-efficient, far-sighted bandwidth allocation policy design for facilitating bursty traffic in a PON framework while satisfying strict QoS (age of information/delay and bandwidth) requirements of modern applications. To this purpose, first we design a delay-tracking mechanism which allows us to model the resource allocation problem from a control-theoretic viewpoint as a Model Predictive Control (MPC). MPC helps in taking far-sighted decisions regarding resource allocations and captures the time-varying dynamics of the network. We provide computationally efficient polynomial-time solutions and show its implementation in the PON framework. Compared to existing approaches, MPC reduces delay violations by approximately 15% for a delay-constrained application of 1ms target. Our approach is also robust to varying traffic arrivals.

cs.NI↗

arXiv2021

A Markov Game Model for AI-based Cyber Security Attack Mitigation

The new generation of cyber threats leverages advanced AI-aided methods, which make them capable to launch multi-stage, dynamic, and effective attacks. Current cyber-defense systems encounter various challenges to defend against such new and emerging threats. Modeling AI-aided threats through game theory models can help the defender to select optimal strategies against the attacks and make wise decisions to mitigate the attack's impact. This paper first explores the current state-of-the-art in the new generation of threats in which AI techniques such as deep neural network is used for the attacker and discusses further challenges. We propose a Markovian dynamic game that can evaluate the efficiency of defensive methods against the AI-aided attacker under a cloud-based system in which the attacker utilizes an AI technique to launch an advanced attack by finding the shortest attack path. We use the CVSS metrics to quantify the values of this zero-sum game model for decision-making.

cs.GT↗

arXiv2020

Defending Regression Learners Against Poisoning Attacks

Regression models, which are widely used from engineering applications to financial forecasting, are vulnerable to targeted malicious attacks such as training data poisoning, through which adversaries can manipulate their predictions. Previous works that attempt to address this problem rely on assumptions about the nature of the attack/attacker or overestimate the knowledge of the learner, making them impractical. We introduce a novel Local Intrinsic Dimensionality (LID) based measure called N-LID that measures the local deviation of a given data point's LID with respect to its neighbors. We then show that N-LID can distinguish poisoned samples from normal samples and propose an N-LID based defense approach that makes no assumptions of the attacker. Through extensive numerical experiments with benchmark datasets, we show that the proposed defense mechanism outperforms the state of the art defenses in terms of prediction accuracy (up to 76% lower MSE compared to an undefended ridge model) and running time.

cs.LG↗

arXiv2020

Defending Distributed Classifiers Against Data Poisoning Attacks

Support Vector Machines (SVMs) are vulnerable to targeted training data manipulations such as poisoning attacks and label flips. By carefully manipulating a subset of training samples, the attacker forces the learner to compute an incorrect decision boundary, thereby cause misclassifications. Considering the increased importance of SVMs in engineering and life-critical applications, we develop a novel defense algorithm that improves resistance against such attacks. Local Intrinsic Dimensionality (LID) is a promising metric that characterizes the outlierness of data samples. In this work, we introduce a new approximation of LID called K-LID that uses kernel distance in the LID calculation, which allows LID to be calculated in high dimensional transformed spaces. We introduce a weighted SVM against such attacks using K-LID as a distinguishing characteristic that de-emphasizes the effect of suspicious data samples on the SVM decision boundary. Each sample is weighted on how likely its K-LID value is from the benign K-LID distribution rather than the attacked K-LID distribution. We then demonstrate how the proposed defense can be applied to a distributed SVM framework through a case study on an SDR-based surveillance system. Experiments with benchmark data sets show that the proposed defense reduces classification error rates substantially (10% on average).

cs.LG↗

arXiv2020

Adversarial Reinforcement Learning under Partial Observability in Autonomous Computer Network Defence

Recent studies have demonstrated that reinforcement learning (RL) agents are susceptible to adversarial manipulation, similar to vulnerabilities previously demonstrated in the supervised learning setting. While most existing work studies the problem in the context of computer vision or console games, this paper focuses on reinforcement learning in autonomous cyber defence under partial observability. We demonstrate that under the black-box setting, where the attacker has no direct access to the target RL model, causative attacks---attacks that target the training process---can poison RL agents even if the attacker only has partial observability of the environment. In addition, we propose an inversion defence method that aims to apply the opposite perturbation to that which an attacker might use to generate their adversarial samples. Our experimental results illustrate that the countermeasure can effectively reduce the impact of the causative attack, while not significantly affecting the training process in non-attack scenarios.

stat.ML↗

arXiv2019

Smart Scheduling and Feedback Allocation over Non-stationary Wireless Channels

It is well known that opportunistic scheduling algorithms are throughput optimal under dynamic channel and network conditions. However, these algorithms achieve a hypothetical rate region which does not take into account the overhead associated with channel probing and feedback required to obtain the full channel state information at every slot. In this work, we design a joint scheduling and channel probing algorithm by considering the overhead of obtaining the channel state information. We adopt a correlated and non-stationary channel model, which is more realistic than those used in the literature. We use concepts from learning and information theory to accurately track channel variations to minimize the number of channels probed at every slot, while scheduling users to maximize the achievable rate region of the network. More specifically, we employ Gaussian Process Regression that enable us to predict future channel state and also provide a way to measure uncertainty in the learning and prediction. Simulation results show that with the proposed algorithm, the network can carry higher user traffic. The proposed solution can be utilized in more complex and heterogeneous environments such as 5G and beyond networks where the model free approach is needed.

cs.NI↗

arXiv2019

A Template and Suggestions for Writing Easy-to-Read Research Articles

The number of research papers written has been growing at least linearly -- if not exponentially -- in recent years. In proportion, the amount of time a reader allocates per paper has been decreasing. While an accessible paper will be appreciated by a large audience, hard-to-read papers may remain obscure for a long time regardless of scientific merit. Unfortunately, there is still insufficient emphasis on good written and oral communication skills in technical disciplines, especially in engineering. As an academic, I have realised over the years that I keep telling my students the same things over and over again when they write papers, reports, presentations, and theses. This article contains some of those suggestions and serves as a limited template for organising research articles. I have adopted a very practical and personal approach and don't claim that this is a formal contribution to the scientific communication literature. However, I hope that this article will not only make my life a bit easier but also help other graduate students and academic supervisors.

cs.GL↗

arXiv2018

Reinforcement Learning for Autonomous Defence in Software-Defined Networking

Despite the successful application of machine learning (ML) in a wide range of domains, adaptability---the very property that makes machine learning desirable---can be exploited by adversaries to contaminate training and evade classification. In this paper, we investigate the feasibility of applying a specific class of machine learning algorithms, namely, reinforcement learning (RL) algorithms, for autonomous cyber defence in software-defined networking (SDN). In particular, we focus on how an RL agent reacts towards different forms of causative attacks that poison its training process, including indiscriminate and targeted, white-box and black-box attacks. In addition, we also study the impact of the attack timing, and explore potential countermeasures such as adversarial training.

cs.CR↗

arXiv2017

Game theoretic path selection to support security in device-to-device communications

Device-to-Device (D2D) communication is expected to be a key feature supported by 5G networks, especially due to the proliferation of Mobile Edge Computing (MEC), which has a prominent role in reducing network stress by shifting computational tasks from the Internet to the mobile edge. Apart from being part of MEC, D2D can extend cellular coverage allowing users to communicate directly when telecommunication infrastructure is highly congested or absent. This significant departure from the typical cellular paradigm imposes the need for decentralised network routing protocols. Moreover, enhanced capabilities of mobile devices and D2D networking will likely result in proliferation of new malware types and epidemics. Although the literature is rich in terms of D2D routing protocols that enhance quality-of-service and energy consumption, they provide only basic security support, e.g., in the form of encryption. Routing decisions can, however, contribute to collaborative detection of mobile malware by leveraging different kinds of anti-malware software installed on mobile devices. Benefiting from the cooperative nature of D2D communications, devices can rely on each other's contributions to detect malware. The impact of our work is geared towards having more malware-free D2D networks. To achieve this, we designed and implemented a novel routing protocol for D2D communications that optimises routing decisions for explicitly improving malware detection. The protocol identifies optimal network paths, in terms of malware mitigation and energy spent for malware detection, based on a game theoretic model. Diverse capabilities of network devices running different types of anti-malware software and their potential for inspecting messages relayed towards an intended destination device are leveraged using game theoretic tools. An optimality analysis of both Nash and Stackelberg security games is undertaken, including both zero and non-zero sum variants, and the Defender's equilibrium strategies. By undertaking network simulations, theoretical results obtained are illustrated through randomly generated network scenarios showing how our protocol outperforms conventional routing protocols, in terms of expected payoff, which consists of: security damage in inflicted by malware and malware detection cost.

cs.GT↗

arXiv2017

Toward the Starting Line: A Systems Engineering Approach to Strong AI

Artificial General Intelligence (AGI) or Strong AI aims to create machines with human-like or human-level intelligence, which is still a very ambitious goal when compared to the existing computing and AI systems. After many hype cycles and lessons from AI history, it is clear that a big conceptual leap is needed for crossing the starting line to kick-start mainstream AGI research. This position paper aims to make a small conceptual contribution toward reaching that starting line. After a broad analysis of the AGI problem from different perspectives, a system-theoretic and engineering-based research approach is introduced, which builds upon the existing mainstream AI and systems foundations. Several promising cross-fertilization opportunities between systems disciplines and AI research are identified. Specific potential research directions are discussed.

cs.AI↗

arXiv2017

Nash Equilibrium Approximation under Communication and Computation Constraints in Large-Scale Non-cooperative Games

This paper studies the problem of Nash equilibrium approximation in large-scale heterogeneous mean-field games under communication and computation constraints. A deterministic mean-field game is considered in which the non-linear utility function of each agent depends on its action, the average of other agents' actions (called the mean variable of that agent) and a deterministic parameter. It is shown that the equilibrium mean variables of all agents converge uniformly to a constant, called asymptotic equilibrium mean (AEM), as the number of agents tends to infinity. The AEM, which depends on the limit of empirical distribution of agents' parameters, determines the asymptotic equilibrium behavior of agents. Next, the problem of approximating the AEM at a processing center under communication and computation constraints is studied. Three approximation methods are proposed to substantially reduce the communication and computation costs of approximating AEM at the processing center. The accuracy of the proposed approximation methods is analyzed and illustrated through numerical examples.

math.OC↗

arXiv2017

Impact of Optimal Storage Allocation on Price Volatility in Electricity Markets

Recent studies show that the fast growing expansion of wind power generation may lead to extremely high levels of price volatility in wholesale electricity markets. Storage technologies, regardless of their specific forms e.g. pump-storage hydro, large-scale or distributed batteries, are capable of alleviating the extreme price volatility levels due to their energy usage time shifting, fast-ramping and price arbitrage capabilities. In this paper, we propose a stochastic bi-level optimization model to find the optimal nodal storage capacities required to achieve a certain price volatility level in a highly volatile electricity market. The decision on storage capacities is made in the upper level problem and the operation of strategic/regulated generation, storage and transmission players is modeled at the lower level problem using an extended Cournot-based stochastic game. The South Australia (SA) electricity market, which has recently experienced high levels of price volatility, is considered as the case study for the proposed storage allocation framework. Our numerical results indicate that 80% price volatility reduction in SA electricity market can be achieved by installing either 340 MWh regulated storage or 420 MWh strategic storage. In other words, regulated storage firms are more efficient in reducing the price volatility than strategic storage firms.

math.OC↗