scholarly journals Generating Adversarial Examples for Holding Robustness of Source Code Processing Models

2020 ◽  
Vol 34 (01) ◽  
pp. 1169-1176
Author(s):  
Huangzhao Zhang ◽  
Zhuo Li ◽  
Ge Li ◽  
Lei Ma ◽  
Yang Liu ◽  
...  
Keyword(s):  
Programming Languages ◽  
State Of The Art ◽  
Source Code ◽  
Natural Languages ◽  
Current State ◽  
Automated Processing ◽  
Adversarial Examples ◽  
Adversarial Training ◽  
New Challenges ◽  
And Performance

Automated processing, analysis, and generation of source code are among the key activities in software and system lifecycle. To this end, while deep learning (DL) exhibits a certain level of capability in handling these tasks, the current state-of-the-art DL models still suffer from non-robust issues and can be easily fooled by adversarial attacks.Different from adversarial attacks for image, audio, and natural languages, the structured nature of programming languages brings new challenges. In this paper, we propose a Metropolis-Hastings sampling-based identifier renaming technique, named \fullmethod (\method), which generates adversarial examples for DL models specialized for source code processing. Our in-depth evaluation on a functionality classification benchmark demonstrates the effectiveness of \method in generating adversarial examples of source code. The higher robustness and performance enhanced through our adversarial training with \method further confirms the usefulness of DL models-based method for future fully automated source code processing.

A Systematic Review of API Evolution Literature

2022 ◽  
Vol 54 (8) ◽  
pp. 1-36
Author(s):  
Maxime Lamothe ◽  
Yann-Gaël Guéhéneuc ◽  
Weiyi Shang
Keyword(s):  
Programming Languages ◽  
Research Evaluation ◽  
State Of The Art ◽  
Publication Trends ◽  
Current State ◽  
Software Artifact ◽  
Application Programming ◽  
New Challenges ◽  
The Impact ◽  
Programming Interfaces

Recent software advances have led to an expansion of the development and usage of application programming interfaces (APIs). From millions of Android packages (APKs) available on Google Store to millions of open-source packages available in Maven, PyPI, and npm, APIs have become an integral part of software development. Like any software artifact, software APIs evolve and suffer from this evolution. Prior research has uncovered many challenges to the development, usage, and evolution of APIs. While some challenges have been studied and solved, many remain. These challenges are scattered in the literature, which hides advances and cloaks the remaining challenges. In this systematic literature review on APIs and API evolution, we uncover and describe publication trends and trending topics. We compile common research goals, evaluation methods, metrics, and subjects. We summarize the current state-of-the-art and outline known existing challenges as well as new challenges uncovered during this review. We conclude that the main remaining challenges related to APIs and API evolution are (1) automatically identifying and leveraging factors that drive API changes, (2) creating and using uniform benchmarks for research evaluation, and (3) understanding the impact of API evolution on API developers and users with respect to various programming languages.

scholarly journals Robust CNN Compression Framework for Security-Sensitive Embedded Systems

2021 ◽  
Vol 11 (3) ◽  
pp. 1093
Author(s):  
Jeonghyun Lee ◽  
Sangkyun Lee
Keyword(s):  
Embedded Systems ◽  
Optimization Problem ◽  
State Of The Art ◽  
Classification Problems ◽  
Proximal Gradient Method ◽  
Knowledge Distillation ◽  
New Type ◽  
Adversarial Examples ◽  
Adversarial Training ◽  
Memory Efficient

Convolutional neural networks (CNNs) have achieved tremendous success in solving complex classification problems. Motivated by this success, there have been proposed various compression methods for downsizing the CNNs to deploy them on resource-constrained embedded systems. However, a new type of vulnerability of compressed CNNs known as the adversarial examples has been discovered recently, which is critical for security-sensitive systems because the adversarial examples can cause malfunction of CNNs and can be crafted easily in many cases. In this paper, we proposed a compression framework to produce compressed CNNs robust against such adversarial examples. To achieve the goal, our framework uses both pruning and knowledge distillation with adversarial training. We formulate our framework as an optimization problem and provide a solution algorithm based on the proximal gradient method, which is more memory-efficient than the popular ADMM-based compression approaches. In experiments, we show that our framework can improve the trade-off between adversarial robustness and compression rate compared to the existing state-of-the-art adversarial pruning approach.

scholarly journals A review on the use of additive manufacturing to produce lower limb orthoses

2019 ◽  
Vol 5 (2) ◽  
pp. 85-94 ◽  
Author(s):  
Mohammed S. Alqahtani ◽  
Abdulsalam Al-Tamimi ◽  
Henrique Almeida ◽  
Glen Cooper ◽  
Paulo Bartolo
Keyword(s):  
Additive Manufacturing ◽  
Lower Limb ◽  
State Of The Art ◽  
Production Costs ◽  
Current State ◽  
Research Challenges ◽  
Fixation Devices ◽  
Alignment Correction ◽  
And Performance

Abstract Orthoses (exoskeletons and fracture fixation devices) enhance users’ ability to function and improve their quality of life by supporting alignment correction, restoring mobility, providing protection, immobilisation and stabilisation. Ideally, these devices should be personalised to each patient to improve comfort and performance. Production costs have been one of the main constraints for the production of personalised orthoses. However, customisation and personalisation of orthoses are now possible through the use of additive manufacturing. This paper presents the current state of the art of additive manufacturing for the fabrication of orthoses, providing several examples, and discusses key research challenges to be addressed to further develop this field.

scholarly journals Integrated Simulation Environment for Unmanned Autonomous Systems—Towards a Conceptual Framework

2010 ◽  
Vol 2010 ◽  
pp. 1-12 ◽  
Author(s):  
M. G. Perhinschi ◽  
M. R. Napolitano ◽  
S. Tamayo
Keyword(s):  
Conceptual Framework ◽  
State Of The Art ◽  
Autonomous Systems ◽  
Simulation Environment ◽  
Integrated Simulation ◽  
Systems Perspective ◽  
Future Developments ◽  
Current State ◽  
And Performance ◽  
Testing And Evaluation

The paper initiates a comprehensive conceptual framework for an integrated simulation environment for unmanned autonomous systems (UAS) that is capable of supporting the design, analysis, testing, and evaluation from a “system of systems” perspective. The paper also investigates the current state of the art of modeling and performance assessment of UAS and their components and identifies directions for future developments. All the components of a comprehensive simulation environment focused on the testing and evaluation of UAS are identified and defined through detailed analysis of current and future required capabilities and performance. The generality and completeness of the simulation environment is ensured by including all operational domains, types of agents, external systems, missions, and interactions between components. The conceptual framework for the simulation environment is formulated with flexibility, modularity, generality, and portability as key objectives. The development of the conceptual framework for the UAS simulation reveals important aspects related to the mechanisms and interactions that determine specific UAS characteristics including complexity, adaptability, synergy, and high impact of artificial and human intelligence on system performance and effectiveness.

scholarly journals Generating Adversarial Examples with Adversarial Networks

2018 ◽  
Author(s):  
Chaowei Xiao ◽  
Bo Li ◽  
Jun-yan Zhu ◽  
Warren He ◽  
Mingyan Liu ◽  
...  
Keyword(s):  
Deep Neural Networks ◽  
State Of The Art ◽  
Black Box ◽  
Generative Adversarial Networks ◽  
Perceptual Quality ◽  
Small Magnitude ◽  
Adversarial Networks ◽  
Original Target ◽  
Adversarial Examples ◽  
Adversarial Training

Deep neural networks (DNNs) have been found to be vulnerable to adversarial examples resulting from adding small-magnitude perturbations to inputs. Such adversarial examples can mislead DNNs to produce adversary-selected results. Different attack strategies have been proposed to generate adversarial examples, but how to produce them with high perceptual quality and more efficiently requires more research efforts. In this paper, we propose AdvGAN to generate adversarial exam- ples with generative adversarial networks (GANs), which can learn and approximate the distribution of original instances. For AdvGAN, once the generator is trained, it can generate perturbations efficiently for any instance, so as to potentially accelerate adversarial training as defenses. We apply Adv- GAN in both semi-whitebox and black-box attack settings. In semi-whitebox attacks, there is no need to access the original target model after the generator is trained, in contrast to traditional white-box attacks. In black-box attacks, we dynamically train a distilled model for the black-box model and optimize the generator accordingly. Adversarial examples generated by AdvGAN on different target models have high attack success rate under state-of-the-art defenses compared to other attacks. Our attack has placed the first with 92.76% accuracy on a public MNIST black-box attack challenge.

Real-time Whiteboard Coding on Mobile Devices

2020 ◽  
Vol 2020 (8) ◽  
pp. 309-1-309-6
Author(s):  
Xunyu Pan ◽  
Colin Crowe ◽  
Toby Myers ◽  
Emily Jetton
Keyword(s):  
Programming Languages ◽  
Mobile Devices ◽  
Error Detection ◽  
Handwriting Recognition ◽  
Source Code ◽  
Coding System ◽  
Natural Languages ◽  
Text Input ◽  
Error Detection And Correction ◽  
Program Output

Mobile devices typically support input from virtual keyboards or pen-based technologies, allowing handwriting to be a potentially viable text input solution for programming on touchscreen devices. The major problem, however, is that handwriting recognition systems are built to take advantage of the rules of natural languages rather than programming languages. In addition, mobile devices are also inherently restricted by the limitation of screen size and the inconvenient use of a virtual keyboard. In this work, we create a novel handwriting-to-code transformation system on a mobile platform to recognize and analyze source code written directly on a whiteboard or a piece of paper. First, the system recognizes and further compiles the handwritten source code into an executable program. Second, a friendly graphical user interface (GUI) is provided to visualize how manipulating different sections of code impacts the program output. Finally, the coding system supports an automatic error detection and correction mechanism to help address the common syntax and spelling errors during the process of whiteboard coding. The mobile application provides a flexible and user-friendly solution for realtime handwriting-based programming for learners under various environments where the keyboard or touchscreen input is not preferred.

scholarly journals Development and Test of Solutions to Enlarge the Power of PV Irrigation and Application to a 140 kW PV-Diesel Representative Case

Energies ◽  
2018 ◽  
Vol 11 (12) ◽  
pp. 3538 ◽  
Author(s):  
Rita H. Almeida ◽  
Isaac B. Carrêlo ◽  
Eduardo Lorenzo ◽  
Luis Narvarte ◽  
José Fernández-Ramos ◽  
...  
Keyword(s):  
State Of The Art ◽  
Economic Feasibility ◽  
Performance Ratio ◽  
Performance Indices ◽  
Pv System ◽  
Levelized Cost Of Electricity ◽  
Current State ◽  
Design Characteristics ◽  
Olive Trees ◽  
And Performance

The current state of the art of photovoltaic (PV) irrigation systems is limited to PV peak powers below 40 kWp, which does not cover the irrigation needs of farmers, co-operatives, irrigator communities, and agro-industries. This limitation of power is due to two main technical barriers: The quick intermittence of PV power due to the passing of clouds, and the maladjustment between PV production and water needs. This paper presents new solutions that have been developed to overcome these barriers and their application to the design and performance of a 140 kWp hybrid PV-diesel system for the drip irrigation of 195 ha of olive trees in Alter do Chão, Portugal. The performance of the solutions was analysed during two years of real operation. As the performance of the PV system is not only affected by intrinsic-to-design characteristics, but also by circumstances external to the system, new performance indices were developed. As an example, the percentage of use of PV electricity, PVSH, was 78% and 82% in 2017 and 2018, respectively, and the performance ratio of the PV part, PRPV, was 0.79 and 0.80. The economic feasibility was also analysed based on experimental data, resulting in savings in the levelized cost of electricity of 61%.

scholarly journals Bidirectional Adversarial Training for Semi-Supervised Domain Adaptation

2020 ◽  
Author(s):  
Pin Jiang ◽  
Aming Wu ◽  
Yahong Han ◽  
Yunfeng Shao ◽  
Meiyu Qi ◽  
...  
Keyword(s):  
Additional Data ◽  
Domain Adaptation ◽  
State Of The Art ◽  
Powerful Method ◽  
Target Domain ◽  
Unsupervised Domain Adaptation ◽  
Benchmark Datasets ◽  
Adversarial Examples ◽  
Adversarial Training ◽  
Effective Use

Semi-supervised domain adaptation (SSDA) is a novel branch of machine learning that scarce labeled target examples are available, compared with unsupervised domain adaptation. To make effective use of these additional data so as to bridge the domain gap, one possible way is to generate adversarial examples, which are images with additional perturbations, between the two domains and fill the domain gap. Adversarial training has been proven to be a powerful method for this purpose. However, the traditional adversarial training adds noises in arbitrary directions, which is inefficient to migrate between domains, or generate directional noises from the source to target domain and reverse. In this work, we devise a general bidirectional adversarial training method and employ gradient to guide adversarial examples across the domain gap, i.e., the Adaptive Adversarial Training (AAT) for source to target domain and Entropy-penalized Virtual Adversarial Training (E-VAT) for target to source domain. Particularly, we devise a Bidirectional Adversarial Training (BiAT) network to perform diverse adversarial trainings jointly. We evaluate the effectiveness of BiAT on three benchmark datasets and experimental results demonstrate the proposed method achieves the state-of-the-art.

scholarly journals Ulixes: Facial Recognition Privacy with Adversarial Machine Learning

2021 ◽  
Vol 2022 (1) ◽  
pp. 148-165
Author(s):  
Thomas Cilloni ◽  
Wei Wang ◽  
Charles Walter ◽  
Charles Fleming
Keyword(s):  
Machine Learning ◽  
State Of The Art ◽  
Facial Recognition ◽  
Clustering Methods ◽  
Non Invasive ◽  
Current State ◽  
Social Media Platforms ◽  
Adversarial Examples ◽  
The Cost ◽  
Photo Management

Abstract Facial recognition tools are becoming exceptionally accurate in identifying people from images. However, this comes at the cost of privacy for users of online services with photo management (e.g. social media platforms). Particularly troubling is the ability to leverage unsupervised learning to recognize faces even when the user has not labeled their images. In this paper we propose Ulixes, a strategy to generate visually non-invasive facial noise masks that yield adversarial examples, preventing the formation of identifiable user clusters in the embedding space of facial encoders. This is applicable even when a user is unmasked and labeled images are available online. We demonstrate the effectiveness of Ulixes by showing that various classification and clustering methods cannot reliably label the adversarial examples we generate. We also study the effects of Ulixes in various black-box settings and compare it to the current state of the art in adversarial machine learning. Finally, we challenge the effectiveness of Ulixes against adversarially trained models and show that it is robust to countermeasures.

Sign in / Sign up

Export Citation Format

Share Document