相关论文: Adaptive Domain Inference Attack with Concept Hier…

In this paper we consider the setting where machine learning models are retrained on updated datasets in order to incorporate the most up-to-date information or reflect distribution shifts. We investigate whether one can infer information…

The collection and availability of big data, combined with advances in pre-trained models (e.g., BERT, XLNET, etc), have revolutionized the predictive performance of modern natural language processing tasks, ranging from text classification…

Recent years have witnessed the tremendous success of diffusion models in data synthesis. However, when diffusion models are applied to sensitive data, they also give rise to severe privacy concerns. In this paper, we systematically present…

In a model extraction attack, an adversary steals a copy of a remotely deployed machine learning model, given oracle prediction access. We taxonomize model extraction attacks around two objectives: *accuracy*, i.e., performing well on the…

State-of-the-art deep neural networks (DNNs) have been proved to have excellent performance on unsupervised domain adaption (UDA). However, recent work shows that DNNs perform poorly when being attacked by adversarial samples, where these…

Model extraction attacks (MEAs) enable an attacker to replicate the functionality of a victim deep neural network (DNN) model by only querying its API service remotely, posing a severe threat to the security and integrity of pay-per-query…

Network Intrusion Detection Systems (NIDS) play a crucial role in safeguarding network infrastructure against cyberattacks. As the prevalence and sophistication of these attacks increase, machine learning and deep neural network approaches…

Model adaptation tackles the distribution shift problem with a pre-trained model instead of raw data, which has become a popular paradigm due to its great privacy protection. Existing methods always assume adapting to a clean target domain,…

Domain adaptation (DA) or domain generalization (DG) for face presentation attack detection (PAD) has attracted attention recently with its robustness against unseen attack scenarios. Existing DA/DG-based PAD methods, however, have not yet…

Unsupervised domain adaptation has recently emerged as an effective paradigm for generalizing deep neural networks to new target domains. However, there is still enormous potential to be tapped to reach the fully supervised performance. In…

Artificial intelligence systems are prevalent in everyday life, with use cases in retail, manufacturing, health, and many other fields. With the rise in AI adoption, associated risks have been identified, including privacy risks to the…

Unsupervised domain adaptation for semantic segmentation aims to make models trained on synthetic data (source domain) adapt to real images (target domain). Previous feature-level adversarial learning methods only consider adapting models…

Gradient inversion attacks on federated learning systems reconstruct client training data from exchanged gradient information. To defend against such attacks, a variety of defense mechanisms were proposed. However, they usually lead to an…

Targeting in-memory one-dimensional search keys, we propose a novel DIstribution-driven Learned Index tree (DILI), where a concise and computation-efficient linear regression model is used for each node. An internal node's key range is…

An adversarial attack paradigm explores various scenarios for the vulnerability of deep learning models: minor changes of the input can force a model failure. Most of the state of the art frameworks focus on adversarial attacks for images…

Model inversion attacks involve reconstructing the training data of a target model, which raises serious privacy concerns for machine learning models. However, these attacks, especially learning-based methods, are likely to suffer from low…

There has been a tremendous progress in Domain Adaptation (DA) for visual recognition tasks. Particularly, open-set DA has gained considerable attention wherein the target domain contains additional unseen categories. Existing open-set DA…

Membership inference attacks have emerged as a significant privacy concern in the training of deep learning models, where attackers can infer whether a data point was part of the training set based on the model's outputs. To address this…

Increasing use of ML technologies in privacy-sensitive domains such as medical diagnoses, lifestyle predictions, and business decisions highlights the need to better understand if these ML technologies are introducing leakages of sensitive…

Adversarial attacks (AAs) pose a significant threat to the reliability and robustness of deep neural networks. While the impact of these attacks on model predictions has been extensively studied, their effect on the learned representations…