Kyushu University Academic Staff Educational and Research Activities Database
List of Presentations
Danilo Vasconcellos Vargas Last modified date:2021.09.03

Associate Professor / Faculty of Information Science and Electrical Engineering, Kyushu University / Department of Informatics / Faculty of Information Science and Electrical Engineering


Presentations
1. Kotyan, S., Vargas, D. V., Is Neural Architecture Search A Way Forward to Develop Robust Neural Networks?, JSAI2020, 2020.07.
2. Anh Duc Ta, Vargas, D. V., Towards improvement of SUNA in Multiplexers with preliminary results of simple Logic Gate neuron variation., GECCO2020 Late Breaking Papers (Companion), 2020.07.
3. Kotyan, S., Vargas, D. V., Towards Evolving Robust Neural Architectures to Defend from Adversarial Attacks., GECCO2020 (Companion), 2020.07.
4. Valencia R., Sham, B., Vargas, D. V., Preliminary study of applied Binary Neural Networks for Neural Cryptography., GECCO2020 (Companion), 2020.07.
5. Kotyan, S., Vargas, D. V., Towards Evolving Robust Neural Architectures to Defend from Adversarial Attacks, IJCAI2020 Workshop AISafety 2020, 2020.07.
6. Vargas, D. V., & Su, J, Understanding the one-pixel attack: Propagation maps and locality analysis, IJCAI2020 Workshop AISafety 2020, 2020.07.
7. Di Li, Danilo Vasconcellos Vargas, Sakurai Kouichi, Universal Rules for Fooling Deep Neural Networks based Text Classification, 2019 IEEE Congress on Evolutionary Computation, CEC 2019, 2019.06, Recently, deep learning based natural language processing techniques are being extensively used to deal with spam mail, censorship evaluation in social networks, among others. However, there is only a couple of works evaluating the vulnerabilities of such deep neural networks. Here, we go beyond attacks to investigate, for the first time, universal rules, i.e., rules that are sample agnostic and therefore could turn any text sample in an adversarial one. In fact, the universal rules do not use any information from the method itself (no information from the method, gradient information or training dataset information is used), making them black-box universal attacks. In other words, the universal rules are sample and method agnostic. By proposing a coevolutionary optimization algorithm we show that it is possible to create universal rules that can automatically craft imperceptible adversarial samples (only less than five perturbations which are close to misspelling are inserted in the text sample). A comparison with a random search algorithm further justifies the strength of the method. Thus, universal rules for fooling networks are here shown to exist. Hopefully, the results from this work will impact the development of yet more sample and model agnostic attacks as well as their defenses..
8. Lia T. Parsenadze, Danilo Vasconcellos Vargas, Toshiyuki Fujita, Towards solving neural networks with optimization trajectory search, 2019 Genetic and Evolutionary Computation Conference, GECCO 2019, 2019.07, Modern gradient based optimization methods for deep neural networks demonstrate outstanding results on image classification tasks. However, methods that do not rely on gradient feedback fail to tackle deep network optimization. In the field of evolutionary computation, applying evolutionary algorithms directly to network weights remains to be an unresolved challenge. In this paper we examine a new framework for the evolution of deep nets. Based on the empirical analysis, we propose the use of linear sub-spaces of problems to search for promising optimization trajectories in parameter space, opposed to weight evolution. We show that linear sub-spaces of loss functions are sufficiently well-behaved to allow trajectory evaluation. Furthermore, we introduce fitness measure to show that it is possible to correctly categorize trajectories according to their distance from the optimal path. As such, this work introduces an alternative approach to evolutionary optimization of deep networks..
9. Vinícius V. De Melo, Danilo Vasconcellos Vargas, Wolfgang Banzhaf, Batch tournament selection for genetic programming, 2019 Genetic and Evolutionary Computation Conference, GECCO 2019, 2019.07, Lexicase selection achieves very good solution quality by introducing ordered test cases. However, the computational complexity of lexicase selection can prohibit its use in many applications. In this paper, we introduce Batch Tournament Selection (BTS), a hybrid of tournament and lexicase selection which is approximately one order of magnitude faster than lexicase selection while achieving a competitive quality of solutions. Tests on a number of regression datasets show that BTS compares well with lexicase selection in terms of mean absolute error while having a speed-up of up to 25 times. Surprisingly, BTS and lexicase selection have almost no difference in both diversity and performance. This reveals that batches and ordered test cases are completely different mechanisms which share the same general principle fostering the specialization of individuals. This work introduces an efficient algorithm that sheds light onto the main principles behind the success of lexicase, potentially opening up a new range of possibilities for algorithms to come..
10. Shashank Kotyan, Danilo Vasconcellos Vargas, U. Venkanna, Self Training Autonomous Driving Agent, 58th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2019, 2019.09, Intrinsically, driving is a Markov Decision Process which suits well the reinforcement learning paradigm. In this paper, we propose a novel agent which learns to drive a vehicle without any human assistance. We use the concept of reinforcement learning and evolutionary strategies to train our agent in a 2D simulation environment. Our model's architecture goes beyond the World Model's by introducing difference images in the autoencoder. This novel involvement of difference images in the auto-encoder gives a better representation of the latent space concerning the motion of the vehicle and helps an autonomous agent to learn more efficiently how to drive a vehicle. Results show that our method requires fewer (96% less) total agents, (87.5% less) agents per generations, (70% less) generations and (90% less) rollouts than the original architecture while achieving the same accuracy of the original..
11. Rui Qiu, Danilo Vasconcellos Vargas, Kouich Sakurai, Frame difference generative adversarial networks
Clearer contour video generating, 7th International Symposium on Computing and Networking Workshops, CANDARW 2019, 2019.11, Generating image and video is a hot topic in Deep Learning. Especially, generating video is a difficult but meaningful work. How to generate video which has diversity and plausibility is still a problem to be solved. In this paper, we propose a novel model of Generative Adversarial Network(GAN) which called FDGAN to generate clear contour lines. Unlike existing GAN that only use frames, our method extends to use inter-frame difference. First introduce two temporal difference methods to process the inter-frame. Then increase a frame difference discriminator to discriminate whether the inter-frame is true or not. Using the model and new structure proposed, we perform video generation experiments on several widely used benchmark datasets such as MOVING MNIST, UCF-101. Consequently, the results achieve state-of-the-art performance for clarifying contour lines. Both quantitative and qualitative evaluations were made to show the effectiveness of our methods..
12. Jean Paulo Martins, Antonio Helson Mineiro Soares, Danilo Vasconcellos Vargas, Alexandre Cláudio Botazzo Delbem, Multi-objective phylogenetic algorithm
Solving multi-objective decomposable deceptive problems, 6th International Conference on Evolutionary Multi-Criterion Optimization, EMO 2011, 2011.04, In general, Multi-objective Evolutionary Algorithms do not guarantee find solutions in the Pareto-optimal set. We propose a new approach for solving decomposable deceptive multi-objective problems that can find all solutions of the Pareto-optimal set. Basically, the proposed approach starts by decomposing the problem into subproblems and, then, combining the found solutions. The resultant approach is a Multi-objective Estimation of Distribution Algorithm for solving relatively complex multi-objective decomposable problems, using a probabilistic model based on a phylogenetic tree. The results show that, for the tested problem, the algorithm can efficiently find all the solutions of the Pareto-optimal set, with better scaling than the hierarchical Bayesian Optimization Algorithm and other algorithms of the state of art..
13. Danilo Vasconcellos Vargas, Hirotaka Takano, Junichi Murata, Continuous adaptive reinforcement learning with the evolution of Self Organizing Classifiers, 2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013, 2013, Learning classifier systems have been solving reinforcement learning problems for some time. However, they face difficulties under multi-step continuous problems. Adaptation may also become harder with time since the convergence of the population decreases its diversity. This article demonstrate that the novel Self Organizing Classifiers method can cope with dynamical multi-step continuous problems. Moreover, adaptation remains the same after convergence..
14. Danilo Vasconcellos Vargas, Hirotaka Takano, Junichi Murata, Contingency training, 2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013, 2013, When applied to high-dimensional datasets, feature selection algorithms might still leave dozens of irrelevant variables in the dataset. Therefore, even after feature selection has been applied, classifiers must be prepared to the presence of irrelevant variables. This paper investigates a new training method called Contingency Training which increases the accuracy as well as the robustness against irrelevant attributes. Contingency training is classifier independent. By subsampling and removing information from each sample, it creates a set of constraints. These constraints aid the method to automatically find proper importance weights of the dataset's features. Experiments are conducted with the contingency training applied to neural networks over traditional datasets as well as datasets with additional irrelevant variables. For all of the tests, contingency training surpassed the unmodified training on datasets with irrelevant variables and even outperformed slightly when only a few or no irrelevant variables were present..
15. Danilo Vasconcellos Vargas, Hirotaka Takano, Junichi Murata, A study on the importance of selection pressure and low dimensional weak learners to produce robust ensembles, 15th Annual Conference on Genetic and Evolutionary Computation, GECCO 2013, 2013, Ensembles of classifiers have been studied for some time. It is widely known that weak learners should be accurate and diverse. However, in the real world there are many constraints and few have been said about the robustness of ensembles and how to develop it. In the context of ran- dom subspace methods, this paper addresses the question of developing ensembles to face problems under time con- straints. Experiments show that selecting weak learners based on their accuracy can be used to create robust en- sembles. Thus, the selection pressure in ensembles is a key technique to create not just effective ensembles but also robust ones. Moreover, the experiments motivate further research on ensembles made of low dimensional classifiers which achieve general accurate results..
16. Danilo Vasconcellos Vargas, Hirotaka Takano, Junichi Murata, Self organizing classifiers and niched fitness, 2013 15th Genetic and Evolutionary Computation Conference, GECCO 2013, 2013.09, Learning classifier systems are adaptive learning systems which have been widely applied in a multitude of application domains. However, there are still some generalization problems unsolved. The hurdle is that fitness and niching pressures are difficult to balance. Here, a new algorithm called Self Organizing Classifiers is proposed which faces this problem from a different perspective. Instead of balancing the pressures, both pressures are separated and no balance is necessary. In fact, the proposed algorithm possesses a dynamical population structure that self-organizes itself to better project the input space into a map. The niched fitness concept is defined along with its dynamical population structure, both are indispensable for the understanding of the proposed method. Promising results are shown on two continuous multi-step problems. One of which is yet more challenging than previous problems of this class in the literature..
17. Danilo Vasconcellos Vargas, Hirotaka Takano, Junichi Murata, Novelty-Organizing Classifiers applied to classification and reinforcement learning
Towards flexible algorithms, 16th Genetic and Evolutionary Computation Conference, GECCO 2014, 2014, It is widely known that reinforcement learning is a more general problem than supervised learning. In fact, supervised learning can be seen as a class of reinforcement learning problems. However, only a couple of papers tested reinforcement learning algorithms in supervised learning problems. Here we propose a new and simpler way to abstract supervised learning for any reinforcement learning algorithm. Moreover, a new algorithm called Novelty-Organizing Classifiers is developed based on a Novelty Map population that focuses more on the novelty of the inputs than their frequency. A comparison of the proposed method with Self-Organizing Classifiers and BioHel on some datasets is presented. Even though BioHel is specialized in solving supervised learning problems, the results showed only a trade-off between the algorithms. Lastly, results on a maze problem validate the flexibility of the proposed algorithm beyond supervised learning problems. Thus, Novelty-Organizing Classifiers is capable of solving many supervised learning problems as well as a maze problem without changing any parameter at all. Considering the fact that no adaptation of parameters was executed, the proposed algorithm's basis seems interestingly flexible..
18. Danilo Vasconcellos Vargas, Hirotaka Takano, Junichi Murata, Novelty-organizing team of classifiers - A team-individual multi-objective approach to reinforcement learning, 2014 53rd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2014, 2014.10, In reinforcement learning, there are basically two spaces to search: value-function space and policy space. Consequently, there are two fitness functions each with their associated trade-offs. However, the problem is still perceived as a single-objective one. Here a multi-objective reinforcement learning algorithm is proposed with a structured novelty map population evolving feedforward neural models. It outperforms a gradient based continuous input-output state-of-art algorithm in two problems. Contrary to the gradient based algorithm, the proposed one solves both problems with the same parameters and smaller variance of results. Moreover, the results are comparable even with other discrete action algorithms of the literature as well as neuroevolution methods such as NEAT. The proposed method brings also the novelty map population concept, i.e., a novelty map-based population which is less sensitive to the input distribution and therefore more suitable to create the state space. In fact, the novelty map framework is shown to be less dynamic and more resource efficient than variants of the self-organizing map..
19. Danilo Vasconcellos Vargas, Hirotaka Takano, Junichi Murata, The relationship between (Un)fractured problems and division of input space, 17th Genetic and Evolutionary Computation Conference, GECCO 2015, 2015.07, Problems can be categorized as fractured or unfractured ones. A different set of characteristics are needed for learning algorithms to solve each of these two types of problems. However, the exact characteristics needed to solve each type are unclear. This article shows that the division of the input space is one of these characteristics. In other words, a study is presented showing that while fractured problems benefit from a finer division of the input space, unfractured problems benefit from a coarser division of input space. Many open questions still remains. And the article discusses two conjectures which can be used to solve fractured problems more easily..
20. Danilo Vasconcellos Vargas, Hirotaka Takano, Junichi Murata, Novelty-Organizing Team of Classifiers in noisy and dynamic environments, IEEE Congress on Evolutionary Computation, CEC 2015, 2015.09, In the real world, the environment is constantly changing with the input variables under the effect of noise. However, few algorithms were shown to be able to work under those circumstances. Here, Novelty-Organizing Team of Classifiers (NOTC) is applied to the continuous action mountain car as well as two variations of it: A noisy mountain car and an unstable weather mountain car. These problems take respectively noise and change of problem dynamics into account. Moreover, NOTC is compared with NeuroEvolution of Augmenting Topologies (NEAT) in these problems, revealing a trade-off between the approaches. While NOTC achieves the best performance in all of the problems, NEAT needs less trials to converge. It is demonstrated that NOTC achieves better performance because of its division of the input space (creating easier problems). Unfortunately, this division of input space also requires a bit of time to bootstrap..
21. Danilo Vasconcellos Vargas, Junichi Murata, Curious
Searching for unknown regions of space with a subpopulation-based algorithm, 2016 Genetic and Evolutionary Computation Conference, GECCO 2016 Companion, 2016.07, Intrinsic motivation and novelty search are promising approaches to deal with plateaus, deceptive functions and other exploration problems where using only the main objective function is insufficient. However, it is not clear until now how and if intrinsic motivation (novelty search) can improve single objective algorithms in general. The hurdle is that using multi-objective algorithms to deal with single-objective problems adds an unnecessary overhead such as the search for non-dominated solutions. Here, we propose the Curious algorithm which is the first multi-objective algorithm focused on solving single-objective problems. Curious uses two subpopulations algorithms. One subpopulation is dedicated for improving objective function values and another one is added to search for unknown regions of space based on objective prediction errors. By using a differential evolution operator, genes from individuals in all subpopulations are mixed. In this way, the promising regions (solutions with high fitness) and unknown regions (solutions with high prediction error) are searched simultaneously. Because of thus realized strong yet well controlled novelty search, the algorithm possesses powerful exploration ability and outperforms usual single population based algorithms such as differential evolution. Thus, it demonstrates that the addition of intrinsic motivation is promising and should improve further single objective algorithms in general..
22. Jiawei Su, Danilo Vasconcellos Vargas, Kouichi Sakurai, Evasion attacks against statistical code obfuscation detectors, 12th International Workshop on Security, IWSEC 2017, 2017.01, In the domain of information security, code obfuscation is a feature often employed for malicious purposes. For example there have been quite a few papers reporting that obfuscated JavaScript frequently comes with malicious functionality such as redirecting to external malicious websites. In order to capture such obfuscation, a class of detectors based on statistical features of code, mostly n-grams have been proposed and been claimed to achieve high detection accuracy. In this paper, we formalize a common scenario between defenders who maintain the statistical obfuscation detectors and adversaries who want to evade the detection. Accordingly, we create two kinds of evasion attack methods and evaluate the robustness of statistical detectors under such attacks. Experimental results show that statistical obfuscation detectors can be easily fooled by a sophisticated adversary even in worst case scenarios..
23. Shiqian Yu, Danilo Vasconcellos Vargas, Kouichi Sakurai, Effectively Protect Your Privacy
Enabling Flexible Privacy Control on Web Tracking, 5th International Symposium on Computing and Networking, CANDAR 2017, 2018.04, Third-party tracking, which can collect the users' privacy when users are surfing the Internet, has garnered much attention. Nowadays tracker-blocking tools often use a ruleset based on the domains and elements that need to be blocked. This results in blocking all access tracking, even though the website shows no sign about tracking users' privacy. And what's more, although the tracker-blocking tools try their best to block all the third-party tracking, not all the users dislike the advertisement. Some of them think if their privacy is fine, it's all right to accept advertisements. In this paper, we present a novel framework by using Word2Vec to block third-party tracking. Our goal is to create more flexible and well-developed ruleset that can help users to protect their privacy according to their needs. Instead of blocking all access tracking, we decide to pay more attention to the websites that have a strong probability to collect the users' privacy. We use Word2Vec to classify the websites, and our results show that after using our framework, the error rate drops from 71% to 24%. We believe it brings the new blood into the field of web privacy by providing not only the new third-party tracking tool but also a novel way of thinking about how to block the third-party tracking..
24. Jiawei Su, Danilo Vasconcellos Vargas, Sanjiva Prasad, Sgandurra Daniele, Yaokai Feng, Kouichi Sakurai, Lightweight Classification of IoT Malware Based on Image Recognition, 42nd IEEE Computer Software and Applications Conference, COMPSAC 2018, 2018.06, The Internet of Things (IoT) is an extension of the traditional Internet, which allows a very large number of smart devices, such as home appliances, network cameras, sensors and controllers to connect to one another to share information and improve user experiences. IoT devices are micro-computers for domain-specific computations rather than traditional functionspecific embedded devices. This opens the possibility of seeing many kinds of existing attacks, traditionally targeted at the Internet, also directed at IoT devices. As shown by recent events, such as the Mirai and Brickerbot botnets, DDoS attacks have become very common in IoT environments as these lack basic security monitoring and protection mechanisms. In this paper, we propose a novel light-weight approach for detecting DDos malware in IoT environments. We extract the malware images (i.e., a one-channel gray-scale image converted from a malware binary) and utilize a light-weight convolutional neural network for classifying their families. The experimental results show that the proposed system can achieve 94:0% accuracy for the classification of goodware and DDoS malware, and 81:8% accuracy for the classification of goodware and two main malware families..
25. Ryan J. Urbanowicz, Danilo Vasconcellos Vargas, Introducing learning classifier systems
Rules that capture complexity, 2018 Genetic and Evolutionary Computation Conference, GECCO 2018, 2018.07.
26. Yao Xu, Hiroshi Koide, Danilo Vasconcellos Vargas, Kouichi Sakurai, Tracing MIRAI malware in networked system, 6th International Symposium on Computing and Networking Workshops, CANDARW 2018, 2018.12, In 2021, it is anticipated that there will be approximately 30 billion Internet of Things (IoT) devices. The tremendous aggregate value of the IoT makes it a tempting and lucrative target for cyber criminals. The breakout of Mirai malware, which compromises poorly secured IoT devices with factory-default username and passphrase to launch Distributed Denial of Service (DDoS) attacks, has raised broad awareness towards the need for increased IoT security. To better defend against Mirai infection and spread, it is critical to know how the malware operates as the first step. In this paper, we give a combined static and dynamic analysis of Mirai, basing on the results of which, we introduce the application of Threat Tracer. Threat tracer is an information system simulator initially developed to help design a system robust against Advanced Persistent Attacks(APT). It offers an intuitive track on how a cyber threat behaves in a complicated networked system. The feedback simultaneously contributes to revealing vulnerabilities of a system. Our work focuses on the replication of Mirai Malware's operating processes in Threat Tracer simulation. By achieving doing so, we believe it could offer a comprehensible description of how Mirai acts. Also, considering the continuous emergence of Mirai variants, the simulation serves as a predictor on upcoming threats' behavior patterns..
27. Yuetong Zhu, Danilo Vasconcellos Vargas, Kouichi Sakurai, Neural cryptography based on the topology evolving neural networks, 6th International Symposium on Computing and Networking Workshops, CANDARW 2018, 2018.12, Modern cryptographic schemes is developed based on the mathematical theory. Recently works show a new direction about cryptography based on the neural networks. Instead of learning a specific algorithm, a cryptographic scheme is generated automatically. While one kind of neural network is used to achieve the scheme, the idea of the neural cryptography can be realized by other neural network architecture is unknown. In this paper, we make use of this property to create neural cryptography scheme on a new topology evolving neural network architecture called Spectrum-diverse unified neuroevolution architecture. First, experiments are conducted to verify that Spectrum-diverse unified neuroevolution architecture is able to achieve automatic encryption and decryption. Subsequently, we do experiments to achieve the neural symmetric cryptosystem by using adversarial training..
28. Jiawei Su, Danilo Vasconcellos Vargas, Kouichi Sakurai, Empirical evaluation on robustness of deep convolutional neural networks activation functions against adversarial perturbation, 6th International Symposium on Computing and Networking Workshops, CANDARW 2018, 2018.12, Recent research has shown that deep convolutional neural networks (DCNN) are vulnerable to several different types of attacks while the reasons of such vulnerability are still under investigation. For instance, the adversarial perturbations can conduct a slight change on a natural image to make the target DCNN make the wrong recognition, while the reasons that DCNN is sensitive to such small modification are divergent from one research to another. In this paper, we evaluate the robustness of two commonly used activation functions of DCNN, namely the sigmoid and ReLu, against the recently proposed low-dimensional one-pixel attack. We show that the choosing of activation functions can be an important factor that influences the robustness of DCNN. The results show that comparing with sigmoid, the ReLu non-linearity is more vulnerable which allows the low dimensional one-pixel attack exploit much higher success rate and confidence of launching the attack. The results give insights on designing new activation functions to enhance the security of DCNN..
29. Wai Kyi Kyi Oo, Hiroshi Koide, Danilo Vasconcellos Vargas, Kouichi Sakurai, A new design for evaluating moving target defense system, 6th International Symposium on Computing and Networking Workshops, CANDARW 2018, 2018.12, Moving Target Defense (MTD) concept has been a feasible idea for reducing the possibility of attack happening through alternation attack surfaces or diversification the attribute or parameters of a protected system. As a result of applying MTD techniques to the system, an attacker would have more difficulties in exploiting a vulnerabilities of the target system. This study proposes an evaluation method of MTD systems combined with several different MTD techniques. The proposed method is a primary step in designing an evaluation model for the effectiveness of MTD. The main goal is to estimate the attack success ratio on the MTD systems mitigating from threats of executable binary file or malware injection. With the proposed evaluation method, we expect to prove that the MTD technology can enhance the security of a web server, and can be applied in a real-world information system. As our preliminary work done, we set up a prototype framework to validate the proposed work in a pseudo-experimental environment..