On the Effects of Skip Connections in Deep Generative Adversarial Models

Developments in digital technology and manufacturing processes have expanded the horizon of designer innovation in creating products. In addition to this, real-time collaborative platforms help designers shorten the product development cycle by enabling collaborations with domain experts from concept generation to product realization and after-market. These collaborations are extending beyond enterprise and national boundaries, contributing to a growing concern among designers regarding the security of their sensitive information such as intellectual property (IP) and trade secrets. The source of such sensitive information leaks could be external (e.g., hacker) or internal (e.g., disgruntled employee) to the collaboration. From a designer's perspective, this fear can inhibit participation in a collaboration even though it might result in better products or services. In this paper, we aim to contextualize this evolving security space by discussing various security practices in digital domains, such as encryption and secret sharing, as well as manufacturing domains, such as physically unclonable function (PUF) and physical part watermarking for anticounterfeiting and tamper evidence purposes. Further, we classify these practices with respect to their performance against different adversarial models for different stages in product development. Such a classification can help designers to make informed decisions regarding security practices during the product realization process.

Download Full-text

Adversarial models and resilient schemes for network coding

2008 IEEE International Symposium on Information Theory ◽

10.1109/isit.2008.4594970 ◽

2008 ◽

Cited By ~ 27

Author(s):

Leah Nutman ◽

Michael Langberg

Keyword(s):

Network Coding ◽

Adversarial Models

Download Full-text

Toward Diverse Text Generation with Inverse Reinforcement Learning

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2018/606 ◽

2018 ◽

Cited By ~ 5

Author(s):

Zhan Shi ◽

Xinchi Chen ◽

Xipeng Qiu ◽

Xuanjing Huang

Keyword(s):

Reinforcement Learning ◽

Generative Models ◽

Training Data ◽

Great Success ◽

Text Generation ◽

Inverse Reinforcement Learning ◽

Reward Function ◽

Total Reward ◽

Policy Gradient ◽

Adversarial Models

Text generation is a crucial task in NLP. Recently, several adversarial generative models have been proposed to improve the exposure bias problem in text generation. Though these models gain great success, they still suffer from the problems of reward sparsity and mode collapse. In order to address these two problems, in this paper, we employ inverse reinforcement learning (IRL) for text generation. Specifically, the IRL framework learns a reward function on training data, and then an optimal policy to maximum the expected total reward. Similar to the adversarial models, the reward and policy function in IRL are optimized alternately. Our method has two advantages: (1) the reward function can produce more dense reward signals. (2) the generation policy, trained by ``entropy regularized'' policy gradient, encourages to generate more diversified texts. Experiment results demonstrate that our proposed method can generate higher quality texts than the previous methods.

Download Full-text

Petri Nets for Adversarial Models using Monte Carlo Simulation

10.2172/1473775 ◽

2018 ◽

Author(s):

Benjamin Wyatt Clegg ◽

David H. Collins, Jr. ◽

Aparna V. Huzurbazar

Keyword(s):

Monte Carlo Simulation ◽

Monte Carlo ◽

Petri Nets ◽

Adversarial Models

Download Full-text

Emergent self-mediating classes in the digital semiosphere: Covid-19 conspiracies and the climate justice movement

Nordic Journal of Media Studies ◽

10.2478/njms-2021-0007 ◽

2021 ◽

Vol 3 (1) ◽

pp. 118-140

Author(s):

John Hartley ◽

Indrek Ibrus ◽

Maarja Ojamaa

Keyword(s):

Media Studies ◽

Data Analytics ◽

Social Classes ◽

Climate Justice ◽

Far Right ◽

Mainstream Media ◽

Knowledge Practices ◽

Adversarial Models ◽

Cultural Science ◽

Climate Crisis

Abstract In this article, we advocate for media studies to adopt a systematic evolutionary-complexity model, in order to link the study of human culture and knowledge practices to the biosphere and geosphere, arguing that such global phenomena require a new kind of cultural science. For this purpose, we extend Juri Lotman's model of the semiosphere to the “digital semiosphere”, superseding inherited adversarial models in both mainstream media and media studies. We contrast the mediation of Covid-19 with that of the climate crisis, using Lotman's model to propose that, in the digital semiosphere, the global emergence of girl-led climate activism and far-right Covid-19 conspiracy groups indicates how new social classes are organising around the means of their own mediation. We discuss ways to study and forecast such emergent processes using the means of cultural data analytics and related approaches.

Download Full-text

Beware the Black-Box: On the Robustness of Recent Defenses to Adversarial Examples

Entropy ◽

10.3390/e23101359 ◽

2021 ◽

Vol 23 (10) ◽

pp. 1359

Author(s):

Kaleel Mahmood ◽

Deniz Gurevin ◽

Marten van van Dijk ◽

Phuoung Ha Nguyen

Keyword(s):

Large Scale ◽

Error Correcting Codes ◽

Black Box ◽

Clear Picture ◽

Buffer Zones ◽

Adversarial Models ◽

Adversarial Examples ◽

Winner Take All ◽

The Relationship ◽

Take All

Many defenses have recently been proposed at venues like NIPS, ICML, ICLR and CVPR. These defenses are mainly focused on mitigating white-box attacks. They do not properly examine black-box attacks. In this paper, we expand upon the analyses of these defenses to include adaptive black-box adversaries. Our evaluation is done on nine defenses including Barrage of Random Transforms, ComDefend, Ensemble Diversity, Feature Distillation, The Odds are Odd, Error Correcting Codes, Distribution Classifier Defense, K-Winner Take All and Buffer Zones. Our investigation is done using two black-box adversarial models and six widely studied adversarial attacks for CIFAR-10 and Fashion-MNIST datasets. Our analyses show most recent defenses (7 out of 9) provide only marginal improvements in security (<25%), as compared to undefended networks. For every defense, we also show the relationship between the amount of data the adversary has at their disposal, and the effectiveness of adaptive black-box attacks. Overall, our results paint a clear picture: defenses need both thorough white-box and black-box analyses to be considered secure. We provide this large scale study and analyses to motivate the field to move towards the development of more robust black-box defenses.

Download Full-text

Analyzing Uncertainty of an Ankle Joint Model with Genetic Algorithm

Materials ◽

10.3390/ma13051175 ◽

2020 ◽

Vol 13 (5) ◽

pp. 1175

Author(s):

Adam Ciszkiewicz

Keyword(s):

Genetic Algorithm ◽

Ankle Joint ◽

Search Space ◽

Joint Model ◽

Biomechanical Modeling ◽

Decision Variable ◽

Biomechanical Models ◽

Adversarial Models ◽

The Difference ◽

Angular Displacements

Recent studies in biomechanical modeling suggest a paradigm shift, in which the parameters of biomechanical models would no longer treated as fixed values but as random variables with, often unknown, distributions. In turn, novel and efficient numerical methods will be required to handle such complicated modeling problems. The main aim of this study was to introduce and verify genetic algorithm for analyzing uncertainty in biomechanical modeling. The idea of the method was to encode two adversarial models within one decision variable vector. These structures would then be concurrently optimized with the objective being the maximization of the difference between their outputs. The approach, albeit expensive numerically, offered a general formulation of the uncertainty analysis, which did not constrain the search space. The second aim of the study was to apply the proposed procedure to analyze the uncertainty of an ankle joint model with 43 parameters and flexible links. The bounds on geometrical and material parameters of the model were set to 0.50 mm and 5.00% respectively. The results obtained from the analysis were unexpected. The two obtained adversarial structures were almost visually indistinguishable and differed up to 38.52% in their angular displacements.

Download Full-text