Related papers: On Success and Simplicity: A Second Look at Transf…

Adversarial attacks and backdoor attacks are two common security threats that hang over deep learning. Both of them harness task-irrelevant features of data in their implementation. Text style is a feature that is naturally irrelevant to…

Transferable adversarial images raise critical security concerns for computer vision systems in real-world, black-box attack scenarios. Although many transfer attacks have been proposed, existing research lacks a systematic and…

The transferability of adversarial perturbations provides an effective shortcut for black-box attacks. Targeted perturbations have greater practicality but are more difficult to transfer between models. In this paper, we experimentally and…

Transfer learning is an exciting area of Natural Language Processing that has the potential to both improve model performance and increase data efficiency. This study explores the effects of varying quantities of target task training data…

6G networks will greatly expand the support for data-oriented, autonomous applications for over the top (OTT) and networking use cases. The success of these use cases will depend on the availability of big data sets which is not practical…

Transferable adversarial examples highlight the vulnerability of deep neural networks (DNNs) to imperceptible perturbations across various real-world applications. While there have been notable advancements in untargeted transferable…

Many machine learning models are vulnerable to adversarial examples: inputs that are specially crafted to cause a machine learning model to produce an incorrect output. Adversarial examples that affect one model often affect another model,…

While conditional diffusion models have achieved remarkable success in various applications, they require abundant data to train from scratch, which is often infeasible in practice. To address this issue, transfer learning has emerged as an…

The idea of style transfer has largely only been explored in image-based tasks, which we attribute in part to the specific nature of loss functions used for style transfer. We propose a general formulation of style transfer as an extension…

We investigate a specific security risk in FL: a group of malicious clients has impacted the model during training by disguising their identities and acting as benign clients but later switching to an adversarial role. They use their data,…

State-of-the-art crowd counting and localization are primarily modeled using two paradigms: density maps and point regression. Given the field's security ramifications, there is active interest in model robustness against adversarial…

Transferable adversarial attacks against Deep neural networks (DNNs) have received broad attention in recent years. An adversarial example can be crafted by a surrogate model and then attack the unknown target model successfully, which…

Model stealing attacks present a dilemma for public machine learning APIs. To protect financial investments, companies may be forced to withhold important information about their models that could facilitate theft, including uncertainty…

We propose a novel adaptive transfer learning framework, learning to transfer learn (L2TL), to improve performance on a target dataset by careful extraction of the related information from a source dataset. Our framework considers…

Adversarial transferability enables black-box attacks on unknown victim deep neural networks (DNNs), rendering attacks viable in real-world scenarios. Current transferable attacks create adversarial perturbation over the entire image,…

Transfer learning has been proven as an effective technique for neural machine translation under low-resource conditions. Existing methods require a common target language, language relatedness, or specific training tricks and regimes. We…

Deploying robots in real-world environments, such as households and manufacturing lines, requires generalization across novel task specifications without violating safety constraints. Linear temporal logic (LTL) is a widely used task…

Transfer learning aims at transferring knowledge from a well-labeled domain to a similar but different domain with limited or no labels. Unfortunately, existing learning-based methods often involve intensive model selection and…

Although many efforts have been made into attack and defense on the 2D image domain in recent years, few methods explore the vulnerability of 3D models. Existing 3D attackers generally perform point-wise perturbation over point clouds,…

Targeted training-set attacks inject malicious instances into the training set to cause a trained model to mislabel one or more specific test instances. This work proposes the task of target identification, which determines whether a…