Related papers: Rethinking Image-Scaling Attacks: The Interplay Be…
Deep learning has become an integral part of various computer vision systems in recent years due to its outstanding achievements for object recognition, facial recognition, and scene understanding. However, deep neural networks (DNNs) are…
Deep learning techniques have shown promising results in image compression, with competitive bitrate and image reconstruction quality from compressed latent. However, while image compression has progressed towards a higher peak…
Control policies, trained using the Deep Reinforcement Learning, have been recently shown to be vulnerable to adversarial attacks introducing even very small perturbations to the policy input. The attacks proposed so far have been designed…
Minute pixel changes in an image drastically change the prediction that the deep learning model makes. One of the most significant problems that could arise due to this, for instance, is autonomous driving. Many methods have been proposed…
Dataset bias is a problem in adversarial machine learning, especially in the evaluation of defenses. An adversarial attack or defense algorithm may show better results on the reported dataset than can be replicated on other datasets. Even…
Deep neural networks remain vulnerable to adversarial examples despite advances in architectures and training paradigms. We investigate how training data characteristics affect adversarial robustness across 36 state-of-the-art vision models…
A fundamental issue in deep learning has been adversarial robustness. As these systems have scaled, such issues have persisted. Currently, large language models (LLMs) with billions of parameters suffer from adversarial attacks just like…
This work examines the vulnerability of multimodal (image + text) models to adversarial threats similar to those discussed in previous literature on unimodal (image- or text-only) models. We introduce realistic assumptions of partial model…
Multimodal large language models (MLLMs) comprise of both visual and textual modalities to process vision language tasks. However, MLLMs are vulnerable to security-related issues, such as jailbreak attacks that alter the model's input to…
With the development of information science and technology, various industries have generated massive amounts of data, and machine learning is widely used in the analysis of big data. However, if the privacy of machine learning…
Deep neural network-based image compression has been extensively studied. However, the model robustness which is crucial to practical application is largely overlooked. We propose to examine the robustness of prevailing learned image…
Decision-based attacks construct adversarial examples against a machine learning (ML) model by making only hard-label queries. These attacks have mainly been applied directly to standalone neural networks. However, in practice, ML models…
Face Recognition (FR) models have been shown to be vulnerable to adversarial examples that subtly alter benign facial images, exposing blind spots in these systems, as well as protecting user privacy. End-to-end FR systems first obtain…
Neural networks play an increasingly important role in the field of machine learning and are included in many applications in society. Unfortunately, neural networks suffer from adversarial samples generated to attack them. However, most of…
In recent years, the security issues of artificial intelligence have become increasingly prominent due to the rapid development of deep learning research and applications. Backdoor attack is an attack targeting the vulnerability of deep…
Machine learning (ML) models deployed in many safety- and business-critical systems are vulnerable to exploitation through adversarial examples. A large body of academic research has thoroughly explored the causes of these blind spots,…
A reliable deepfake detector or spoofing countermeasure (CM) should be robust in the face of unpredictable spoofing attacks. To encourage the learning of more generaliseable artefacts, rather than those specific only to known attacks, CMs…
We consider the blackbox transfer-based targeted adversarial attack threat model in the realm of deep neural network (DNN) image classifiers. Rather than focusing on crossing decision boundaries at the output layer of the source model, our…
Machine learning based system are increasingly being used for sensitive tasks such as security surveillance, guiding autonomous vehicle, taking investment decisions, detecting and blocking network intrusion and malware etc. However, recent…
Deep image classification models trained on vast amounts of web-scraped data are susceptible to data poisoning - a mechanism for backdooring models. A small number of poisoned samples seen during training can severely undermine a model's…