Related papers: A Training-Free Defense Framework for Robust Learn…

In this paper we present an end-to-end meta-learned system for image compression. Traditional machine learning based approaches to image compression train one or more neural network for generalization performance. However, at inference…

Numerous safety- or security-critical systems depend on cameras to perceive their surroundings, further allowing artificial intelligence (AI) to analyze the captured images to make important decisions. However, a concerning attack vector…

Most adversarial attack defense methods rely on obfuscating gradients. These methods are successful in defending against gradient-based attacks; however, they are easily circumvented by attacks which either do not use the gradient or by…

Deep Neural Networks (DNNs) are notoriously vulnerable to adversarial input designs with limited noise budgets. While numerous successful attacks with subtle modifications to original input have been proposed, defense techniques against…

Deep learning based image compression has recently witnessed exciting progress and in some cases even managed to surpass transform coding based approaches that have been established and refined over many decades. However, state-of-the-art…

Recent advances in text-to-image generative models provide the ability to generate high-quality images from short text descriptions. These foundation models, when pre-trained on billion-scale datasets, are effective for various downstream…

While deep convolutional neural networks (CNNs) are vulnerable to adversarial attacks, considerably few efforts have been paid to construct robust deep tracking algorithms against adversarial attacks. Current studies on adversarial attack…

Given access to a machine learning model, can an adversary reconstruct the model's training data? This work studies this question from the lens of a powerful informed adversary who knows all the training data points except one. By…

We investigate if the random feature selection approach proposed in [1] to improve the robustness of forensic detectors to targeted attacks, can be extended to detectors based on deep learning features. In particular, we study the…

The widespread adoption of deep neural networks in computer vision applications has brought forth a significant interest in adversarial robustness. Existing research has shown that maliciously perturbed inputs specifically tailored for a…

Deep networks are highly vulnerable to adversarial attacks, yet conventional attack methods utilize static adversarial perturbations that induce fixed mispredictions. In this work, we exploit an overlooked property of adversarial…

DNNs' demand for massive data forces practitioners to collect data from the Internet without careful check due to the unacceptable cost, which brings potential risks of backdoor attacks. A backdoored model always predicts a target class in…

Robustness to adversarial attacks was shown to require a larger model capacity, and thus a larger memory footprint. In this paper, we introduce an approach to obtain robust yet compact models by pruning randomly-initialized binary networks.…

Backdoor attacks pose a serious security threat for training neural networks as they surreptitiously introduce hidden functionalities into a model. Such backdoors remain silent during inference on clean inputs, evading detection due to…

Adversarial machine learning is a well-studied field of research where an adversary causes predictable errors in a machine learning algorithm through precise manipulation of the input. Numerous techniques have been proposed to harden…

We introduce a novel approach to counter adversarial attacks, namely, image resampling. Image resampling transforms a discrete image into a new one, simulating the process of scene recapturing or rerendering as specified by a geometrical…

Recent researches show that deep learning model is susceptible to backdoor attacks. Many defenses against backdoor attacks have been proposed. However, existing defense works require high computational overhead or backdoor attack…

Adversarial training is one of the most popular ways to learn robust models but is usually attack-dependent and time costly. In this paper, we propose the MACER algorithm, which learns robust models without using adversarial training but…

Deep learning models are vulnerable to various adversarial manipulations of their training data, parameters, and input sample. In particular, an adversary can modify the training data and model parameters to embed backdoors into the model,…

With exponential growth in the use of digital image data, the need for efficient transmission methods has become imperative. Traditional image compression techniques often sacrifice image fidelity for reduced file sizes, challenging…