Related papers: CLOAK: Contrastive Guidance for Latent Diffusion-B…
Counterfactual explanations have emerged as a promising method for elucidating the behavior of opaque black-box models. Recently, several works leveraged pixel-space diffusion models for counterfactual generation. To handle noisy,…
Many applications that benefit from data offload to cloud services operate on private data. A now-long line of work has shown that, even when data is offloaded in an encrypted form, an adversary can learn sensitive information by analyzing…
High-dimensional data must be highly structured to be learnable. Although the compositional and hierarchical nature of data is often put forward to explain learnability, quantitative measurements establishing these properties are scarce.…
Recent deep learning models have shown remarkable performance in image classification. While these deep learning systems are getting closer to practical deployment, the common assumption made about data is that it does not carry any…
Makeup transfer aims to apply the makeup style from a reference face to a target face and has been increasingly adopted in practical applications. Existing GAN-based approaches typically rely on carefully designed loss functions to balance…
Invisibility or cloaking has captured human's imagination for many years. With the recent advancement of metamaterials, several theoretical proposals show cloaking of objects is possible, however, so far there is a lack of an experimental…
A new type of cloak is discussed: one that gives all cloaked objects the appearance of a flat conducting sheet. It has the advantage that none of the parameters of the cloak is singular and can in fact be made isotropic. It makes broadband…
Intelligent, large-scale IoT ecosystems have become possible due to recent advancements in sensing technologies, distributed learning, and low-power inference in embedded devices. In traditional cloud-centric approaches, raw data is…
Recent studies have shown that deep neural networks (DNN) are vulnerable to adversarial samples: maliciously-perturbed samples crafted to yield incorrect model outputs. Such attacks can severely undermine DNN systems, particularly in…
Visual counterfactual explanations are ideal hypothetical images that change the decision-making of the classifier with high confidence toward the desired class while remaining visually plausible and close to the initial image. In this…
Deep clustering methods typically rely on a single, well-defined representation for clustering. In contrast, pretrained diffusion models provide abundant and diverse multi-scale representations across network layers and noise timesteps.…
The remarkable success of machine learning has fostered a growing number of cloud-based intelligent services for mobile users. Such a service requires a user to send data, e.g. image, voice and video, to the provider, which presents a…
Detecting falsified faces generated by Deepfake technology is essential for safeguarding trust in digital communication and protecting individuals. However, current detectors often suffer from a dual-overfitting: they become overly…
Federated learning (FL) has been widely studied recently due to its property to collaboratively train data from different devices without sharing the raw data. Nevertheless, recent studies show that an adversary can still be possible to…
Federated learning promises to make machine learning feasible on distributed, private datasets by implementing gradient descent using secure aggregation methods. The idea is to compute a global weight update without revealing the…
Recent years have witnessed the success of diffusion models in image customization tasks. However, existing mask-guided human erasing methods still struggle in complex scenarios such as human-human occlusion, human-object entanglement, and…
The rapid growth of social media has led to the widespread sharing of individual portrait images, which pose serious privacy risks due to the capabilities of automatic face recognition (AFR) systems for mass surveillance. Hence, protecting…
Protecting personal data against exploitation of machine learning models is crucial. Recently, availability attacks have shown great promise to provide an extra layer of protection against the unauthorized use of data to train neural…
The healthcare industry generates troves of unlabelled physiological data. This data can be exploited via contrastive learning, a self-supervised pre-training method that encourages representations of instances to be similar to one another.…
In this paper we investigate the usage of adversarial perturbations for the purpose of privacy from human perception and model (machine) based detection. We employ adversarial perturbations for obfuscating certain variables in raw data…