Related papers: Matryoshka: Stealing Functionality of Private ML D…
The huge computation demand of deep learning models and limited computation resources on the edge devices calls for the cooperation between edge device and cloud service by splitting the deep models into two halves. However, transferring…
In this paper, we reveal a significant shortcoming in class unlearning evaluations: overlooking the underlying class geometry can cause privacy leakage. We further propose a simple yet effective solution to mitigate this issue. We introduce…
Steganography is the art of hiding the fact that communication is taking place, by hiding information in other information. Different types of carrier file formats can be used, but digital images are the most popular ones because of their…
To circumvent the unbridled and ever-encroaching surveillance and censorship in cyberspace, steganography has garnered attention for its ability to hide private information in innocent-looking carriers. Current provably secure steganography…
In today's world the art of sending & displaying the hidden information especially in public places, has received more attention and faced many challenges. Therefore, different methods have been proposed so far for hiding information in…
The integration of Differential Privacy (DP) with diffusion models (DMs) presents a promising yet challenging frontier, particularly due to the substantial memorization capabilities of DMs that pose significant privacy risks. Differential…
We study a setting of collecting and learning from private data distributed across end users. In the shuffled model of differential privacy, the end users partially protect their data locally before sharing it, and their data is also…
Differential privacy (DP) is a formal privacy framework that enables training machine learning (ML) models while protecting individuals' data. As pointed out by prior work, ML models are part of larger systems, which can lead to so-called…
Differential privacy (DP) is the prevailing technique for protecting user data in machine learning models. However, deficits to this framework include a lack of clarity for selecting the privacy budget $\epsilon$ and a lack of…
Deep Neural Networks (DNNs) have become an essential component in many application domains including web-based services. A variety of these services require high throughput and (close to) real-time features, for instance, to respond or…
Recent developments in cloud storage architectures have originated new models of online storage as cooperative storage systems and interconnected clouds. Such distributed environments involve many organizations, thus ensuring…
Training deep neural networks often forces users to work in a distributed or outsourced setting, accompanied with privacy concerns. Split learning aims to address this concern by distributing the model among a client and a server. The…
Privacy-sensitive users require deploying large language models (LLMs) within their own infrastructure (on-premises) to safeguard private data and enable customization. However, vulnerabilities in local environments can lead to unauthorized…
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…
Machine learning models are vulnerable to membership inference attacks in which an adversary aims to predict whether or not a particular sample was contained in the target model's training dataset. Existing attack methods have commonly…
Audio steganography is a collection of techniques for concealing the existence of information by embedding it within a non-secret audio, which is referred to as carrier. Distinct from cryptography, the steganography put emphasis on the…
Digital steganography is becoming a common tool for protecting sensitive communications in various applications such as crime(terrorism) prevention whereby law enforcing personals need to remotely compare facial images captured at the scene…
Machine Learning has been successfully applied in systems applications such as memory prefetching and caching, where learned models have been shown to outperform heuristics. However, the lack of understanding the inner workings of these…
Deep neural networks are normally executed in the forward direction. However, in this work, we identify a vulnerability that enables models to be trained in both directions and on different tasks. Adversaries can exploit this capability to…
Steganography is a general term referring to all methods for the embedding of additional secret content into some form of carrier, with the aim of concealment of the introduced alterations. The choice of the carrier is nearly unlimited, it…