Related papers: Online Adversarial Purification based on Self-Supe…
Recent contrastive methods show significant improvement in self-supervised learning in several domains. In particular, contrastive methods are most effective where data augmentation can be easily constructed e.g. in computer vision.…
Deep neural networks (DNNs) are vulnerable to adversarial noise. Preprocessing based defenses could largely remove adversarial noise by processing inputs. However, they are typically affected by the error amplification effect, especially in…
Smart speakers and voice-based virtual assistants are core components for the success of the IoT paradigm. Unfortunately, they are vulnerable to various privacy threats exploiting machine learning to analyze the generated encrypted traffic.…
Online algorithm is an important branch in algorithm design. Designing online algorithms with a bounded competitive ratio (in terms of worst-case performance) can be hard and usually relies on problem-specific assumptions. Inspired by…
Data privacy is an increasingly important aspect of many real-world Data sources that contain sensitive information may have immense potential which could be unlocked using the right privacy enhancing transformations, but current methods…
Deep Neural Networks (DNNs) have become a powerful toolfor a wide range of problems. Yet recent work has found an increasing variety of adversarial samplesthat can fool them. Most existing detection mechanisms against adversarial…
Adversarial training provides a means of regularizing supervised learning algorithms while virtual adversarial training is able to extend supervised learning algorithms to the semi-supervised setting. However, both methods require making…
Deep neural networks (DNNs) have been shown to be vulnerable to adversarial examples, which can produce erroneous predictions by injecting imperceptible perturbations. In this work, we study the transferability of adversarial examples,…
Deep neural networks (DNNs) could be deceived by generating human-imperceptible perturbations of clean samples. Therefore, enhancing the robustness of DNNs against adversarial attacks is a crucial task. In this paper, we aim to train robust…
In this work, we investigate semi-supervised learning (SSL) for image classification using adversarial training. Previous results have illustrated that generative adversarial networks (GANs) can be used for multiple purposes. Triple-GAN,…
Deep models are highly susceptible to adversarial attacks. Such attacks are carefully crafted imperceptible noises that can fool the network and can cause severe consequences when deployed. To encounter them, the model requires training…
Self-supervised learning of convolutional neural networks can harness large amounts of cheap unlabeled data to train powerful feature representations. As surrogate task, we jointly address ordering of visual data in the spatial and temporal…
Adversarial attacks exploit the vulnerabilities of convolutional neural networks by introducing imperceptible perturbations that lead to misclassifications, exposing weaknesses in feature representations and decision boundaries. This paper…
Although depth extraction with passive sensors has seen remarkable improvement with deep learning, these approaches may fail to obtain correct depth if they are exposed to environments not observed during training. Online adaptation, where…
Adversarial training has become one of the most effective methods for improving robustness of neural networks. However, it often suffers from poor generalization on both clean and perturbed data. In this paper, we propose a new algorithm,…
Deep neural networks have been shown to perform well in many classical machine learning problems, especially in image classification tasks. However, researchers have found that neural networks can be easily fooled, and they are surprisingly…
Adversarial training (AT) for robust representation learning and self-supervised learning (SSL) for unsupervised representation learning are two active research fields. Integrating AT into SSL, multiple prior works have accomplished a…
Multimodal Large Language Models (MLLMs) have achieved remarkable success in tasks such as image captioning, visual question answering, and cross-modal reasoning by integrating visual and textual modalities. However, their multimodal nature…
Pre-training is known to generate universal representations for downstream tasks in large-scale deep learning such as large language models. Existing literature, e.g., \cite{kim2020adversarial}, empirically observe that the downstream tasks…
We propose a new regularization method based on virtual adversarial loss: a new measure of local smoothness of the conditional label distribution given input. Virtual adversarial loss is defined as the robustness of the conditional label…