相关论文: Analysis and Mitigations of Reverse Engineering At…

Deep Neural Networks (DNNs) have tremendous potential in advancing the vision for self-driving cars. However, the security of DNN models in this context leads to major safety implications and needs to be better understood. We consider the…

Natural language processing models have experienced a significant upsurge in recent years, with numerous applications being built upon them. Many of these applications require fine-tuning generic base models on customized, proprietary…

Recent research has established the possibility of deducing soft-biometric attributes such as age, gender and race from an individual's face image with high accuracy. However, this raises privacy concerns, especially when face images…

Deep learning achieves outstanding results in many machine learning tasks. Nevertheless, it is vulnerable to backdoor attacks that modify the training set to embed a secret functionality in the trained model. The modified training samples…

Recent studies revealed that deep neural networks (DNNs) are exposed to backdoor threats when training with third-party resources (such as training samples or backbones). The backdoored model has promising performance in predicting benign…

Consumer and defense systems demanded design and manufacturing of electronics with increased performance, compared to their predecessors. As such systems became ubiquitous in a plethora of domains, their application surface increased, thus…

The incremental diffusion of machine learning algorithms in supporting cybersecurity is creating novel defensive opportunities but also new types of risks. Multiple researches have shown that machine learning methods are vulnerable to…

Fine-tuning is a common and effective method for tailoring large language models (LLMs) to specialized tasks and applications. In this paper, we study the privacy implications of fine-tuning LLMs on user data. To this end, we consider a…

Adversarial attacks involve adding, small, often imperceptible, perturbations to inputs with the goal of getting a machine learning model to misclassifying them. While many different adversarial attack strategies have been proposed on image…

Machine learning models have demonstrated promising performance in many areas. However, the concerns that they can be biased against specific demographic groups hinder their adoption in high-stake applications. Thus, it is essential to…

Deep learning models are usually black boxes when deployed on machine learning platforms. Prior works have shown that the attributes ($e.g.$, the number of convolutional layers) of a target black-box neural network can be exposed through a…

Adversarial attacks are small, carefully crafted perturbations, imperceptible to the naked eye; that when added to an image cause deep learning models to misclassify the image with potentially detrimental outcomes. With the rise of…

Current adversarial attack research reveals the vulnerability of learning-based classifiers against carefully crafted perturbations. However, most existing attack methods have inherent limitations in cross-dataset generalization as they…

With an ever-increasing reliance on machine learning (ML) models in the real world, adversarial examples threaten the safety of AI-based systems such as autonomous vehicles. In the image domain, they represent maliciously perturbed data…

Authentication systems are vulnerable to model inversion attacks where an adversary is able to approximate the inverse of a target machine learning model. Biometric models are a prime candidate for this type of attack. This is because…

Privacy-preserving inference in edge computing paradigms encourages the users of machine-learning services to locally run a model on their private input and only share the models outputs for a target task with the server. We study how a…

Being able to reconstruct training data from the parameters of a neural network is a major privacy concern. Previous works have shown that reconstructing training data, under certain circumstances, is possible. In this work, we analyse such…

Recent studies demonstrated the vulnerability of control policies learned through deep reinforcement learning against adversarial attacks, raising concerns about the application of such models to risk-sensitive tasks such as autonomous…

Federated learning offers a privacy-preserving framework for medical image analysis but exposes the system to adversarial attacks. This paper aims to evaluate the vulnerabilities of federated learning networks in medical image analysis…

The ubiquitous use of face recognition has sparked increasing privacy concerns, as unauthorized access to sensitive face images could compromise the information of individuals. This paper presents an in-depth study of the privacy protection…