Related papers: Gray-box Adversarial Testing for Control Systems w…
Throughout the past five years, the susceptibility of neural networks to minimal adversarial perturbations has moved from a peculiar phenomenon to a core issue in Deep Learning. Despite much attention, however, progress towards more robust…
In this paper, we consider the problem of formally verifying a Neural Network (NN) based autonomous landing system. In such a system, a NN controller processes images from a camera to guide the aircraft while approaching the runway. A…
Machine learning (ML) models, e.g., deep neural networks (DNNs), are vulnerable to adversarial examples: malicious inputs modified to yield erroneous model outputs, while appearing unmodified to human observers. Potential attacks include…
The use of neural networks as function approximators has enabled many advances in reinforcement learning (RL). The generalization power of neural networks combined with advances in RL algorithms has reignited the field of artificial…
DNN is presenting human-level performance for many complex intelligent tasks in real-world applications. However, it also introduces ever-increasing security concerns. For example, the emerging adversarial attacks indicate that even very…
Deep Neural Networks are powerful tools to understand complex patterns and making decisions. However, their black-box nature impedes a complete understanding of their inner workings. While online saliency-guided training methods try to…
Testing is essential for verifying and validating control designs, especially in safety-critical applications. In particular, the control system governing an automated driving vehicle must be proven reliable enough for its acceptance on the…
We consider adversarial training of deep neural networks through the lens of Bayesian learning, and present a principled framework for adversarial training of Bayesian Neural Networks (BNNs) with certifiable guarantees. We rely on…
Adversarial Training has proved to be an effective training paradigm to enforce robustness against adversarial examples in modern neural network architectures. Despite many efforts, explanations of the foundational principles underpinning…
Machine Learning systems are vulnerable to adversarial attacks and will highly likely produce incorrect outputs under these attacks. There are white-box and black-box attacks regarding to adversary's access level to the victim learning…
Deep reinforcement learning has the potential to address various scientific problems. In this paper, we implement an optics simulation environment for reinforcement learning based controllers. The environment captures the essence of…
Powerful adversarial attack methods are vital for understanding how to construct robust deep neural networks (DNNs) and for thoroughly testing defense techniques. In this paper, we propose a black-box adversarial attack algorithm that can…
In recent years, deep reinforcement learning (Deep RL) has been successfully implemented as a smart agent in many systems such as complex games, self-driving cars, and chat-bots. One of the interesting use cases of Deep RL is its…
Despite the impressive performances reported by deep neural networks in different application domains, they remain largely vulnerable to adversarial examples, i.e., input samples that are carefully perturbed to cause misclassification at…
Optimization-based controller tuning is challenging because it requires formulating optimization problems explicitly as functions of controller parameters. Safe learning algorithms overcome the challenge by creating surrogate models from…
Deep neural networks are at the forefront of machine learning research. However, despite achieving impressive performance on complex tasks, they can be very sensitive: Small perturbations of inputs can be sufficient to induce incorrect…
We propose a detector of adversarial samples that is based on the view of neural networks as discrete dynamic systems. The detector tells clean inputs from abnormal ones by comparing the discrete vector fields they follow through the…
In this paper, we propose a framework for performing state space exploration of closed loop control systems. Our approach involves approximating sensitivity and a newly introduced notion of inverse sensitivity by a neural network. We show…
Complex autonomous control systems are subjected to sensor failures, cyber-attacks, sensor noise, communication channel failures, etc. that introduce errors in the measurements. The corrupted information, if used for making decisions, can…
Adversarial examples are maliciously tweaked images that can easily fool machine learning techniques, such as neural networks, but they are normally not visually distinguishable for human beings. One of the main approaches to solve this…