相关论文: Defense Against Model Stealing Based on Account-Aw…

Deep Neural Networks (DNNs) are susceptible to model stealing attacks, which allows a data-limited adversary with no knowledge of the training dataset to clone the functionality of a target model, just by using black-box query access. Such…

Recent research demonstrates that GNNs are vulnerable to the model stealing attack, a nefarious endeavor geared towards duplicating the target model via query permissions. However, they mainly focus on node classification tasks, neglecting…

Traditional countermeasures against attacks targeting the receiver in quantum key distribution (QKD) systems often suffer from poor compatibility with deployed infrastructure, the risk of introducing new vulnerabilities, and limited…

Machine learning (ML) applications are increasingly prevalent. Protecting the confidentiality of ML models becomes paramount for two reasons: (a) a model can be a business advantage to its owner, and (b) an adversary may use a stolen model…

Anomaly detection (AD) is the machine learning task of identifying highly discrepant abnormal samples by solely relying on the consistency of the normal training samples. Under the constraints of a distribution shift, the assumption that…

Imitation learning has been widely used to learn control policies for autonomous driving based on pre-recorded data. However, imitation learning based policies have been shown to be susceptible to compounding errors when encountering states…

The vulnerability of smartphones to cyberattacks has been a severe concern to users arising from the integrity of installed applications (\textit{apps}). Although applications are to provide legitimate and diversified on-the-go services,…

Diffusion models (DMs) have emerged as a powerful class of generative AI models, showing remarkable potential in anomaly detection (AD) tasks across various domains, such as cybersecurity, fraud detection, healthcare, and manufacturing. The…

While state-of-the-art Deep Neural Network (DNN) models are considered to be robust to random perturbations, it was shown that these architectures are highly vulnerable to deliberately crafted perturbations, albeit being…

Recent works have demonstrated convolutional neural networks are vulnerable to adversarial examples, i.e., inputs to machine learning models that an attacker has intentionally designed to cause the models to make a mistake. To improve the…

Graph Neural Networks (GNNs) achieve high performance in various real-world applications, such as drug discovery, traffic states prediction, and recommendation systems. The fact that building powerful GNNs requires a large amount of…

Deep neural networks are vulnerable to adversarial examples, i.e., carefully-perturbed inputs aimed to mislead classification. This work proposes a detection method based on combining non-linear dimensionality reduction and density…

Federated Learning (FL) is a distributed machine learning diagram that enables multiple clients to collaboratively train a global model without sharing their private local data. However, FL systems are vulnerable to attacks that are…

Medical multimodal large language models (MLLMs) are becoming an instrumental part of healthcare systems, assisting medical personnel with decision making and results analysis. Models for radiology report generation are able to interpret…

A significant threat to the recent, wide deployment of machine learning-based systems, including deep neural networks (DNNs), is adversarial learning attacks. We analyze possible test-time evasion-attack mechanisms and show that, in some…

High-performance Deep Neural Networks (DNNs) are increasingly deployed in many real-world applications e.g., cloud prediction APIs. Recent advances in model functionality stealing attacks via black-box access (i.e., inputs in, predictions…

Adversarial poisoning attacks pose huge threats to various machine learning applications. Especially, the recent accumulative poisoning attacks show that it is possible to achieve irreparable harm on models via a sequence of imperceptible…

Modern applications of artificial neural networks have yielded remarkable performance gains in a wide range of tasks. However, recent studies have discovered that such modelling strategy is vulnerable to Adversarial Examples, i.e. examples…

In this paper, we study the differences and commonalities between statistically out-of-distribution (OOD) samples and adversarial (Adv) samples, both of which hurting a text classification model's performance. We conduct analyses to compare…

Detecting out of distribution (OOD) samples is of paramount importance in all Machine Learning applications. Deep generative modeling has emerged as a dominant paradigm to model complex data distributions without labels. However, prior work…