Dependability Analysis of Deep Reinforcement Learning based Robotics and Autonomous Systems

While Deep Reinforcement Learning (DRL) provides transformational capabilities to the control of Robotics and Autonomous Systems (RAS), the black-box nature of DRL and uncertain deployment-environments of RAS pose new challenges on its dependability. Although there are many existing works imposing constraints on the DRL policy to ensure a successful completion of the mission, it is far from adequate in terms of assessing the DRL-driven RAS in a holistic way considering all dependability properties. In this paper, we formally define a set of dependability properties in temporal logic and construct a Discrete-Time Markov Chain (DTMC) to model the dynamics of risk/failures of a DRL-driven RAS interacting with the stochastic environment. We then do Probabilistic Model Checking based on the designed DTMC to verify those properties. Our experimental results show that the proposed method is effective as a holistic assessment framework, while uncovers conflicts between the properties that may need trade-offs in the training. Moreover, we find the standard DRL training cannot improve dependability properties, thus requiring bespoke optimisation objectives concerning them. Finally, our method offers a novel dependability analysis to the Sim-to-Real challenge of DRL.

Adversarial Robustness of Deep Learning: Theory, Algorithms, and Applications

This tutorial aims to introduce the fundamentals of adversarial robustness of deep learning, presenting a well-structured review of up-to-date techniques to assess the vulnerability of various types of deep learning models to adversarial examples. This tutorial will particularly highlight state-of-the-art techniques in adversarial attacks and robustness verification of deep neural networks (DNNs). We will also introduce some effective countermeasures to improve the robustness of deep learning models, with a particular focus on adversarial training. We aim to provide a comprehensive overall picture about this emerging direction and enable the community to be aware of the urgency and importance of designing robust deep learning models in safety-critical data analytical applications, ultimately enabling the end-users to trust deep learning classifiers. We will also summarize potential research directions concerning the adversarial robustness of deep learning, and its potential benefits to enable accountable and trustworthy deep learning-based data analytical systems and applications.

Learning Robust Variational Information Bottleneck with Reference

We propose a new approach to train a variational information bottleneck (VIB) that improves its robustness to adversarial perturbations. Unlike the traditional methods where the hard labels are usually used for the classification task, we refine the categorical class information in the training phase with soft labels which are obtained from a pre-trained reference neural network and can reflect the likelihood of the original class labels. We also relax the Gaussian posterior assumption in the VIB implementation by using the mutual information neural estimation. Extensive experiments have been performed with the MNIST and CIFAR-10 datasets, and the results show that our proposed approach significantly outperforms the benchmarked models.

A Little Energy Goes a Long Way: Energy-Efficient, Accurate Conversion from Convolutional Neural Networks to Spiking Neural Networks

Spiking neural networks (SNNs) offer an inherent ability to process spatial-temporal data, or in other words, realworld sensory data, but suffer from the difficulty of training high accuracy models. A major thread of research on SNNs is on converting a pre-trained convolutional neural network (CNN) to an SNN of the same structure. State-of-the-art conversion methods are approaching the accuracy limit, i.e., the near-zero accuracy loss of SNN against the original CNN. However, we note that this is made possible only when significantly more energy is consumed to process an input. In this paper, we argue that this trend of energy for accuracy is not necessary -- a little energy can go a long way to achieve the near-zero accuracy loss. Specifically, we propose a novel CNN-to-SNN conversion method that is able to use a reasonably short spike train (e.g., 256 timesteps for CIFAR10 images) to achieve the near-zero accuracy loss. The new conversion method, named as explicit current control (ECC), contains three techniques (current normalisation, thresholding for residual elimination, and consistency maintenance for batch-normalisation), in order to explicitly control the currents flowing through the SNN when processing inputs. We implement ECC into a tool nicknamed SpKeras, which can conveniently import Keras CNN models and convert them into SNNs. We conduct an extensive set of experiments with the tool -- working with VGG16 and various datasets such as CIFAR10 and CIFAR100 -- and compare with state-of-the-art conversion methods. Results show that ECC is a promising method that can optimise over energy consumption and accuracy loss simultaneously.

BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations

Given the pressing need for assuring algorithmic transparency, Explainable AI (XAI) has emerged as one of the key areas of AI research. In this paper, we develop a novel Bayesian extension to the LIME framework, one of the most widely used approaches in XAI -- which we call BayLIME. Compared to LIME, BayLIME exploits prior knowledge and Bayesian reasoning to improve both the consistency in repeated explanations of a single prediction and the robustness to kernel settings. BayLIME also exhibits better explanation fidelity than the state-of-the-art (LIME, SHAP and GradCAM) by its ability to integrate prior knowledge from, e.g., a variety of other XAI techniques, as well as verification and validation (V&V) methods. We demonstrate the desirable properties of BayLIME through both theoretical analysis and extensive experiments.

Towards the Quantification of Safety Risks in Deep Neural Networks

Safety concerns on the deep neural networks (DNNs) have been raised when they are applied to critical sectors. In this paper, we define safety risks by requesting the alignment of the networks decision with human perception. To enable a general methodology for quantifying safety risks, we define a generic safety property and instantiate it to express various safety risks. For the quantification of risks, we take the maximum radius of safe norm balls, in which no safety risk exists. The computation of the maximum safe radius is reduced to the computation of their respective Lipschitz metrics - the quantities to be computed. In addition to the known adversarial example, reachability example, and invariant example, in this paper we identify a new class of risk - uncertainty example - on which humans can tell easily but the network is unsure. We develop an algorithm, inspired by derivative-free optimization techniques and accelerated by tensor-based parallelization on GPUs, to support efficient computation of the metrics. We perform evaluations on several benchmark neural networks, including ACSC-Xu, MNIST, CIFAR-10, and ImageNet networks. The experiments show that, our method can achieve competitive performance on safety quantification in terms of the tightness and the efficiency of computation. Importantly, as a generic approach, our method can work with a broad class of safety risks and without restrictions on the structure of neural networks.

Explaining Image Classifiers using Statistical Fault Localization

The black-box nature of deep neural networks (DNNs) makes it impossible to understand why a particular output is produced, creating demand for Explainable AI. In this paper, we show that statistical fault localization (SFL) techniques from software engineering deliver high quality explanations of the outputs of DNNs, where we define an explanation as a minimal subset of features sufficient for making the same decision as for the original input. We present an algorithm and a tool called DeepCover, which synthesizes a ranking of the features of the inputs using SFL and constructs explanations for the decisions of the DNN based on this ranking. We compare explanations produced by DeepCover with those of the state-of-the-art tools GradCAM, LIME, SHAP, RISE and Extremal and show that explanations generated by DeepCover are consistently better across a broad set of experiments. On a benchmark set with known ground truth, DeepCover achieves 76.7% accuracy, which is 6% better than the second best Extremal.

Reachability Analysis of Deep Neural Networks with Provable Guarantees

Verifying correctness of deep neural networks (DNNs) is challenging. We study a generic reachability problem for feed-forward DNNs which, for a given set of inputs to the network and a Lipschitz-continuous function over its outputs, computes the lower and upper bound on the function values. Because the network and the function are Lipschitz continuous, all values in the interval between the lower and upper bound are reachable. We show how to obtain the safety verification problem, the output range analysis problem and a robustness measure by instantiating the reachability problem. We present a novel algorithm based on adaptive nested optimisation to solve the reachability problem. The technique has been implemented and evaluated on a range of DNNs, demonstrating its efficiency, scalability and ability to handle a broader class of networks than state-of-the-art verification approaches.