Related papers: PUREVQ-GAN: Defending Data Poisoning Attacks throu…
Classical techniques for protecting facial image privacy typically fall into two categories: data-poisoning methods, exemplified by Fawkes, which introduce subtle perturbations to images, or anonymization methods that generate images…
Recently, self-supervised learning (SSL) was shown to be vulnerable to patch-based data poisoning backdoor attacks. It was shown that an adversary can poison a small part of the unlabeled data so that when a victim trains an SSL model on…
Transfer learning for GANs successfully improves generation performance under low-shot regimes. However, existing studies show that the pretrained model using a single benchmark dataset is not generalized to various target datasets. More…
The utility of tabular data for tasks ranging from model training to large-scale data analysis is often constrained by privacy concerns or regulatory hurdles. While existing data generation methods, particularly those based on Generative…
In adversarial machine learning, new defenses against attacks on deep learning systems are routinely broken soon after their release by more powerful attacks. In this context, forensic tools can offer a valuable complement to existing…
Deep learning has achieved enormous success in various industrial applications. Companies do not want their valuable data to be stolen by malicious employees to train pirated models. Nor do they wish the data analyzed by the competitors…
Generative Adversarial Networks (GANs) have shown considerable promise for mitigating the challenge of data scarcity when building machine learning-driven analysis algorithms. Specifically, a number of studies have shown that GAN-based…
Several companies often safeguard their trained deep models (i.e., details of architecture, learnt weights, training details etc.) from third-party users by exposing them only as black boxes through APIs. Moreover, they may not even provide…
Data scarcity in pharmaceutical research has led to reliance on labour-intensive trial-and-error approaches for development rather than data-driven methods. While Machine Learning offers a solution, existing datasets are often small and…
Backdoor and data poisoning attacks can achieve high attack success while evading existing spectral and optimisation based defences. We show that this behaviour is not incidental, but arises from a fundamental geometric mechanism in input…
GAN is a deep-learning based generative approach to generate contents such as images, languages and speeches. Recently, studies have shown that GAN can also be applied to generative adversarial attack examples to fool the machine-learning…
We present variational generative adversarial networks, a general learning framework that combines a variational auto-encoder with a generative adversarial network, for synthesizing images in fine-grained categories, such as faces of a…
Poisoning attacks can disproportionately influence model behaviour by making small changes to the training corpus. While defences against specific poisoning attacks do exist, they in general do not provide any guarantees, leaving them…
We propose Unbalanced GANs, which pre-trains the generator of the generative adversarial network (GAN) using variational autoencoder (VAE). We guarantee the stable training of the generator by preventing the faster convergence of the…
With the broad application of deep neural networks (DNNs), backdoor attacks have gradually attracted attention. Backdoor attacks are insidious, and poisoned models perform well on benign samples and are only triggered when given specific…
Neural speech synthesis techniques have enabled highly realistic speech deepfakes, posing major security risks. Speech deepfake detection is challenging due to distribution shifts across spoofing methods and variability in speakers,…
The Controller Area Network (CAN) protocol is a standard for in-vehicle communication but remains susceptible to cyber-attacks due to its lack of built-in security. This paper presents a multi-stage intrusion detection framework leveraging…
Generative Adversarial Networks (GANs) have become a very popular tool for implicitly learning high-dimensional probability distributions. Several improvements have been made to the original GAN formulation to address some of its…
Retrieval-Augmented Generation (RAG) improves the reliability of large language model applications by grounding generation in retrieved evidence, but it also introduces a new attack surface: corpus poisoning. In this setting, an adversary…
Vector Quantized Variational Autoencoders (VQ-VAEs) are fundamental models that compress continuous visual data into discrete tokens. Existing methods have tried to improve the quantization strategy for better reconstruction quality,…