Related papers: Learning Better Certified Models from Empirically-…
Adversarial examples pose a security threat to many critical systems built on neural networks (such as face recognition systems, and self-driving cars). While many methods have been proposed to build robust models, how to build certifiably…
Deep Neural Network-based systems are now the state-of-the-art in many robotics tasks, but their application in safety-critical domains remains dangerous without formal guarantees on network robustness. Small perturbations to sensor inputs…
Neural network (NN) controllers achieve strong empirical performance on nonlinear dynamical systems, yet deploying them in safety-critical settings requires robustness to disturbances and uncertainty. We present a method for jointly…
Adversarial robustness is a research area that has recently received a lot of attention in the quest for trustworthy artificial intelligence. However, recent works on adversarial robustness have focused on supervised learning where it is…
Modern neural networks are powerful predictive models. However, when it comes to recognizing that they may be wrong about their predictions, they perform poorly. For example, for one of the most common activation functions, the ReLU and its…
Recent studies have shown that robustness to adversarial attacks can be transferred across networks. In other words, we can make a weak model more robust with the help of a strong teacher model. We ask if instead of learning from a static…
Training deep neural network classifiers that are certifiably robust against adversarial attacks is critical to ensuring the security and reliability of AI-controlled systems. Although numerous state-of-the-art certified training methods…
Knowledge distillation optimises a smaller student model to behave similarly to a larger teacher model, retaining some of the performance benefits. While this method can improve results on in-distribution examples, it does not necessarily…
Unlike existing knowledge distillation methods focus on the baseline settings, where the teacher models and training strategies are not that strong and competing as state-of-the-art approaches, this paper presents a method dubbed DIST to…
Knowledge distillation (KD) has been widely used in teacher-student training, with applications to model compression in resource-constrained deep learning. Current works mainly focus on preserving the accuracy of the teacher model. However,…
Adversarial training, which is to enhance robustness against adversarial attacks, has received much attention because it is easy to generate human-imperceptible perturbations of data to deceive a given deep neural network. In this paper, we…
Deep neural network-based image compression (NIC) has achieved excellent performance, but NIC method models have been shown to be susceptible to backdoor attacks. Adversarial training has been validated in image compression models as a…
Adversarial training has been widely explored for mitigating attacks against deep models. However, most existing works are still trapped in the dilemma between higher accuracy and stronger robustness since they tend to fit a model towards…
Knowledge distillation (KD) has received much attention due to its success in compressing networks to allow for their deployment in resource-constrained systems. While the problem of adversarial robustness has been studied before in the KD…
Despite extraordinary progress, current machine learning systems have been shown to be brittle against adversarial examples: seemingly innocuous but carefully crafted perturbations of test examples that cause machine learning predictors to…
While neural networks have achieved high performance in different learning tasks, their accuracy drops significantly in the presence of small adversarial perturbations to inputs. Defenses based on regularization and adversarial training are…
Data-driven models, especially deep learning classifiers often demonstrate great success on clean datasets. Yet, they remain vulnerable to common data distortions such as adversarial and common corruption perturbations. These perturbations…
Recent works have shown the effectiveness of randomized smoothing as a scalable technique for building neural network-based classifiers that are provably robust to $\ell_2$-norm adversarial perturbations. In this paper, we employ…
The robustness of deep neural networks (DNNs) against adversarial example attacks has raised wide attention. For smoothed classifiers, we propose the worst-case adversarial loss over input distributions as a robustness certificate. Compared…
Neural networks have demonstrated considerable success on a wide variety of real-world problems. However, networks trained only to optimize for training accuracy can often be fooled by adversarial examples - slightly perturbed inputs that…