Houssem Ben Braiek

Thomas Reid

2024-10-26

Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering (published)

Trimming the Risk: Towards Reliable Continuous Training for Deep Learning Inspection Systems

Altaf Allah Abbassi

Thomas Reid

2024-09-12

ArXiv (preprint)

Machine Learning Robustness: A Primer

This chapter explores the foundational concept of robustness in Machine Learning (ML) and its integral role in establishing trustworthiness … (see more)in Artificial Intelligence (AI) systems. The discussion begins with a detailed definition of robustness, portraying it as the ability of ML models to maintain stable performance across varied and unexpected environmental conditions. ML robustness is dissected through several lenses: its complementarity with generalizability; its status as a requirement for trustworthy AI; its adversarial vs non-adversarial aspects; its quantitative metrics; and its indicators such as reproducibility and explainability. The chapter delves into the factors that impede robustness, such as data bias, model complexity, and the pitfalls of underspecified ML pipelines. It surveys key techniques for robustness assessment from a broad perspective, including adversarial attacks, encompassing both digital and physical realms. It covers non-adversarial data shifts and nuances of Deep Learning (DL) software testing methodologies. The discussion progresses to explore amelioration strategies for bolstering robustness, starting with data-centric approaches like debiasing and augmentation. Further examination includes a variety of model-centric methods such as transfer learning, adversarial training, and randomized smoothing. Lastly, post-training methods are discussed, including ensemble techniques, pruning, and model repairs, emerging as cost-effective strategies to make models more resilient against the unpredictable. This chapter underscores the ongoing challenges and limitations in estimating and achieving ML robustness by existing approaches. It offers insights and directions for future research on this crucial concept, as a prerequisite for trustworthy AI systems.

2024-03-31

ArXiv (preprint)

Robustness assessment of hyperspectral image CNNs using metamorphic testing

Rached Bouchoucha

Sonia Bouzidi

Rania Zaatour

2023-09-30

Information and Software Technology (published)

Testing Feedforward Neural Networks Training Programs

2023-05-25

ACM Transactions on Software Engineering and Methodology (published)

SmOOD: Smoothness-based Out-of-Distribution Detection Approach for Surrogate Neural Networks in Aircraft Design

Ali Tfaily

Thomas Reid

Ciro Guida

2023-01-04

Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering (published)

An Intentional Forgetting-Driven Self-Healing Method for Deep Reinforcement Learning Systems

Ahmed Haj Yahmed

Rached Bouchoucha

Deep reinforcement learning (DRL) is increasingly applied in large-scale productions like Netflix and Facebook. As with most data-driven sys… (see more)tems, DRL systems can exhibit undesirable behaviors due to environmental drifts, which often occur in constantly-changing production settings. Continual Learning (CL) is the inherent self-healing approach for adapting the DRL agent in response to the environment's conditions shifts. However, successive shifts of considerable magnitude may cause the production environment to drift from its original state. Recent studies have shown that these environmental drifts tend to drive CL into long, or even unsuccessful, healing cycles, which arise from inefficiencies such as catastrophic forgetting, warm-starting failure, and slow convergence. In this paper, we propose Dr. DRL, an effective self-healing approach for DRL systems that integrates a novel mechanism of intentional forgetting into vanilla CL (i.e., standard CL) to overcome its main issues. Dr. DRL deliberately erases the DRL system's minor behaviors to systematically prioritize the adaptation of the key problem-solving skills. Using well-established DRL algorithms, Dr. DRL is compared with vanilla CL on various drifted environments. Dr. DRL is able to reduce, on average, the healing time and fine-tuning episodes by, respectively, 18.74% and 17.72%. Dr. DRL successfully helps agents to adapt to 19.63% of drifted environments left unsolved by vanilla CL while maintaining and even enhancing by up to 45% the obtained rewards for drifted environments that are resolved by both approaches.

2022-12-31

2023 38th IEEE/ACM International Conference on Automated Software Engineering (ASE) (published)

Physics-Guided Adversarial Machine Learning for Aircraft Systems Simulation

Thomas Reid

In the context of aircraft system performance assessment, deep learning technologies allow us to quickly infer models from experimental meas… (see more)urements, with less detailed system knowledge than usually required by physics-based modeling. However, this inexpensive model development also comes with new challenges regarding model trustworthiness. This article presents a novel approach, physics-guided adversarial machine learning (ML), which improves the confidence over the physics consistency of the model. The approach performs, first, a physics-guided adversarial testing phase to search for test inputs revealing behavioral system inconsistencies, while still falling within the range of foreseeable operational conditions. Then, it proceeds with a physics-informed adversarial training to teach the model the system-related physics domain foreknowledge through iteratively reducing the unwanted output deviations on the previously uncovered counterexamples. Empirical evaluation on two aircraft system performance models shows the effectiveness of our adversarial ML approach in exposing physical inconsistencies of both the models and in improving their propensity to be consistent with physics domain knowledge.

2022-12-31

IEEE Transactions on Reliability (published)

DiverGet: A Search-Based Software Testing Approach for Deep Neural Network Quantization Assessment

Ahmed Haj Yahmed

Sonia Bouzidi

Rania Zaatour

Quantization is one of the most applied Deep Neural Network (DNN) compression strategies, when deploying a trained DNN model on an embedded … (see more)system or a cell phone. This is owing to its simplicity and adaptability to a wide range of applications and circumstances, as opposed to specific Artificial Intelligence (AI) accelerators and compilers that are often designed only for certain specific hardware (e.g., Google Coral Edge TPU). With the growing demand for quantization, ensuring the reliability of this strategy is becoming a critical challenge. Traditional testing methods, which gather more and more genuine data for better assessment, are often not practical because of the large size of the input space and the high similarity between the original DNN and its quantized counterpart. As a result, advanced assessment strategies have become of paramount importance. In this paper, we present DiverGet, a search-based testing framework for quantization assessment. DiverGet defines a space of metamorphic relations that simulate naturally-occurring distortions on the inputs. Then, it optimally explores these relations to reveal the disagreements among DNNs of different arithmetic precision. We evaluate the performance of DiverGet on state-of-the-art DNNs applied to hyperspectral remote sensing images. We chose the remote sensing DNNs as they're being increasingly deployed at the edge (e.g., high-lift drones) in critical domains like climate change research and astronomy. Our results show that DiverGet successfully challenges the robustness of established quantization techniques against naturally-occurring shifted data, and outperforms its most recent concurrent, DiffChaser, with a success rate that is (on average) four times higher.

2022-10-05

Empirical Software Engineering (published)

Faults in deep reinforcement learning programs: a taxonomy and a detection approach

Amin Nikanjam

Mohammad Mehdi Morovati

2021-12-19

Automated Software Engineering (published)

Automatic Fault Detection for Deep Learning Programs Using Graph Transformations

Amin Nikanjam

Mohammad Mehdi Morovati

Nowadays, we are witnessing an increasing demand in both corporates and academia for exploiting Deep Learning (DL) to solve complex real-wor… (see more)ld problems. A DL program encodes the network structure of a desirable DL model and the process by which the model learns from the training dataset. Like any software, a DL program can be faulty, which implies substantial challenges of software quality assurance, especially in safety-critical domains. It is therefore crucial to equip DL development teams with efficient fault detection techniques and tools. In this paper, we propose NeuraLint, a model-based fault detection approach for DL programs, using meta-modelling and graph transformations. First, we design a meta-model for DL programs that includes their base skeleton and fundamental properties. Then, we construct a graph-based verification process that covers 23 rules defined on top of the meta-model and implemented as graph transformations to detect faults and design inefficiencies in the generated models (i.e., instances of the meta-model). First, the proposed approach is evaluated by finding faults and design inefficiencies in 28 synthesized examples built from common problems reported in the literature. Then NeuraLint successfully finds 64 faults and design inefficiencies in 34 real-world DL programs extracted from Stack Overflow posts and GitHub repositories. The results show that NeuraLint effectively detects faults and design issues in both synthesized and real-world examples with a recall of 70.5 % and a precision of 100 %. Although the proposed meta-model is designed for feedforward neural networks, it can be extended to support other neural network architectures such as recurrent neural networks. Researchers can also expand our set of verification rules to cover more types of issues in DL programs.

2021-09-27

ACM Transactions on Software Engineering and Methodology (published)

Models of Computational Profiles to Study the Likelihood of DNN Metamorphic Test Cases

Ettore Merlo

Mira Marhaba

Giuliano Antoniol

Neural network test cases are meant to exercise different reasoning paths in an architecture and used to validate the prediction outcomes. I… (see more)n this paper, we introduce "computational profiles" as vectors of neuron activation levels. We investigate the distribution of computational profile likelihood of metamorphic test cases with respect to the likelihood distributions of training, test and error control cases. We estimate the non-parametric probability densities of neuron activation levels for each distinct output class. Probabilities are inferred using training cases only, without any additional knowledge about metamorphic test cases. Experiments are performed by training a network on the MNIST Fashion library of images and comparing prediction likelihoods with those obtained from error control-data and from metamorphic test cases. Experimental results show that the distributions of computational profile likelihood for training and test cases are somehow similar, while the distribution of the random-noise control-data is always remarkably lower than the observed one for the training and testing sets. In contrast, metamorphic test cases show a prediction likelihood that lies in an extended range with respect to training, tests, and random noise. Moreover, the presented approach allows the independent assessment of different training classes and experiments to show that some of the classes are more sensitive to misclassifying metamorphic test cases than other classes. In conclusion, metamorphic test cases represent very aggressive tests for neural network architectures. Furthermore, since metamorphic test cases force a network to misclassify those inputs whose likelihood is similar to that of training cases, they could also be considered as adversarial attacks that evade defenses based on computational profile likelihood evaluation.

2021-07-27

arXiv (Cornell University) (preprint)