Related papers: On the Importance of Encrypting Deep Features

Intrusion Detection Systems (IDS) have an increasingly important role in preventing exploitation of network vulnerabilities by malicious actors. Recent deep learning based developments have resulted in significant improvements in the…

Integrating machine learning into the internals of database management systems requires significant feature engineering, a human effort-intensive process to determine the best way to represent the pieces of information that are relevant to…

It is commonplace to produce application-specific models by fine-tuning large pre-trained models using a small bespoke dataset. The widespread availability of foundation model checkpoints on the web poses considerable risks, including the…

Ideas from Fourier analysis have been used in cryptography for the last three decades. Akavia, Goldwasser and Safra unified some of these ideas to give a complete algorithm that finds significant Fourier coefficients of functions on any…

Embeddings are functions that map raw input data to low-dimensional vector representations, while preserving important semantic information about the inputs. Pre-training embeddings on a large amount of unlabeled data and fine-tuning them…

Deep learning is a powerful weapon to boost application performance in many fields, including face recognition, object detection, image classification, natural language understanding, and recommendation system. With the rapid increase in…

Backdoor attacks aim to inject a backdoor into a classifier such that it predicts any input with an attacker-chosen backdoor trigger as an attacker-chosen target class. Existing backdoor attacks require either retraining the classifier with…

The monitoring of individuals/objects has become increasingly possible in recent years due to the convenience of integrated cameras in many devices. Due to the important moments or activities of people captured by these devices, it has made…

Recent works have demonstrated the feasibility of inverting face recognition systems, enabling to recover convincing face images using only their embeddings. We leverage such template inversion models to develop a novel type ofdeep morphing…

Membership inference attacks are designed to determine, using black box access to trained models, whether a particular example was used in training or not. Membership inference can be formalized as a hypothesis testing problem. The most…

Secure signal processing is becoming a de facto model for preserving privacy. We propose a model based on the Fully Homomorphic Encryption (FHE) technique to mitigate security breaches. Our framework provides a method to perform a Fast…

Deep models are state-of-the-art for many computer vision tasks including image classification and object detection. However, it has been shown that deep models are vulnerable to adversarial examples. We highlight how one-hot encoding…

Recent work has shown that deep-learning algorithms for malware detection are also susceptible to adversarial examples, i.e., carefully-crafted perturbations to input malware that enable misleading classification. Although this has…

Deep learning has come a long way and has enjoyed an unprecedented success. Despite high accuracy, however, deep models are brittle and are easily fooled by imperceptible adversarial perturbations. In contrast to common inference-time…

Constructing high-quality features is critical to any quantitative data analysis. While feature engineering was historically addressed by carefully hand-crafting data representations based on domain expertise, deep neural networks (DNNs)…

In a backdoor attack on a machine learning model, an adversary produces a model that performs well on normal inputs but outputs targeted misclassifications on inputs containing a small trigger pattern. Model compression is a widely-used…

In the recent past, different researchers have proposed privacy-enhancing face recognition systems designed to conceal soft-biometric attributes at feature level. These works have reported impressive results, but generally did not consider…

Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs). In addition, AEs have adversarial transferability, which means AEs generated for a source model can fool another black-box model (target model) with…

Backdoor attacks allow an attacker to embed a specific vulnerability in a machine learning algorithm, activated when an attacker-chosen pattern is presented, causing a specific misprediction. The need to identify backdoors in biometric…

A distribution inference attack aims to infer statistical properties of data used to train machine learning models. These attacks are sometimes surprisingly potent, but the factors that impact distribution inference risk are not well…