Related papers: Causal Information Bottleneck Boosts Adversarial R…
Deep learning models (with neural networks) have been widely used in challenging tasks such as computer-aided disease diagnosis based on medical images. Recent studies have shown deep diagnostic models may not be robust in the inference…
Deep neural networks are vulnerable to so-called adversarial examples: inputs which are intentionally constructed to cause the model to make incorrect predictions or classifications. Adversarial examples are often visually indistinguishable…
Causal Neural Network models have shown high levels of robustness to adversarial attacks as well as an increased capacity for generalisation tasks such as few-shot learning and rare-context classification compared to traditional Neural…
Combining the Information Bottleneck model with deep learning by replacing mutual information terms with deep neural nets has proved successful in areas ranging from generative modelling to interpreting deep neural networks. In this paper,…
Existing deep neural networks, say for image classification, have been shown to be vulnerable to adversarial images that can cause a DNN misclassification, without any perceptible change to an image. In this work, we propose shock absorbing…
In the last a few decades, deep neural networks have achieved remarkable success in machine learning, computer vision, and pattern recognition. Recent studies however show that neural networks (both shallow and deep) may be easily fooled by…
Invariant risk minimization (IRM) has recently emerged as a promising alternative for domain generalization. Nevertheless, the loss function is difficult to optimize for nonlinear classifiers and the original optimization objective could…
Deep neural network-based image compression has been extensively studied. However, the model robustness which is crucial to practical application is largely overlooked. We propose to examine the robustness of prevailing learned image…
The Information Bottleneck (IB) method (\cite{tishby2000information}) provides an insightful and principled approach for balancing compression and prediction for representation learning. The IB objective $I(X;Z)-\beta I(Y;Z)$ employs a…
The vulnerability to slight input perturbations is a worrying yet intriguing property of deep neural networks (DNNs). Despite many previous works studying the reason behind such adversarial behavior, the relationship between the…
Recent studies have found that deep learning systems are vulnerable to adversarial examples; e.g., visually unrecognizable adversarial images can easily be crafted to result in misclassification. The robustness of neural networks has been…
Adversarial attacks insert small, imperceptible perturbations to input samples that cause large, undesired changes to the output of deep learning models. Despite extensive research on generating adversarial attacks and building defense…
Large language models (LLMs) have recently demonstrated remarkable progress in reasoning capabilities through reinforcement learning with verifiable rewards (RLVR). By leveraging simple rule-based rewards, RL effectively incentivizes LLMs…
We introduce a Noise-based prior Learning (NoL) approach for training neural networks that are intrinsically robust to adversarial attacks. We find that the implicit generative modeling of random noise with the same loss function used…
Deep neural networks for computer vision are deployed in increasingly safety-critical and socially-impactful applications, motivating the need to close the gap in model performance under varied, naturally occurring imaging conditions.…
The information bottleneck principle provides an information-theoretic method for representation learning, by training an encoder to retain all information which is relevant for predicting the label while minimizing the amount of other,…
Neural Networks (NNs) are vulnerable to adversarial examples. Such inputs differ only slightly from their benign counterparts yet provoke misclassifications of the attacked NNs. The required perturbations to craft the examples are often…
Capsule networks (CapsNets) are superior at modeling hierarchical spatial relationships but suffer from two critical limitations: high computational cost due to iterative dynamic routing and poor robustness under input corruptions. To…
This paper investigates task-oriented communication for edge inference, where a low-end edge device transmits the extracted feature vector of a local data sample to a powerful edge server for processing. It is critical to encode the data…
The vulnerability of deep neural networks (DNNs) to adversarial attack, which is an attack that can mislead state-of-the-art classifiers into making an incorrect classification with high confidence by deliberately perturbing the original…