相关论文: Towards Privacy-Preserving Visual Recognition via …

With the rapid development of Artificial Intelligence (AI), the problem of AI security has gradually emerged. Most existing machine learning algorithms may be attacked by adversarial examples. An adversarial example is a slightly modified…

The impact of inference-time data perturbation (e.g., adversarial attacks) has been extensively studied in machine learning, leading to well-established certification techniques for adversarial robustness. In contrast, certifying models…

Imitation learning can reproduce policies by observing experts, which poses a problem regarding policy privacy. Policies, such as human, or policies on deployed robots, can all be cloned without consent from the owners. How can we protect…

Supervised learning-based adversarial attack detection methods rely on a large number of labeled data and suffer significant performance degradation when applying the trained model to new domains. In this paper, we propose a self-supervised…

Learning with graphs has attracted significant attention recently. Existing representation learning methods on graphs have achieved state-of-the-art performance on various graph-related tasks such as node classification, link prediction,…

Complex autonomous control systems are subjected to sensor failures, cyber-attacks, sensor noise, communication channel failures, etc. that introduce errors in the measurements. The corrupted information, if used for making decisions, can…

We study statistical risk minimization problems under a privacy model in which the data is kept confidential even from the learner. In this local privacy framework, we establish sharp upper and lower bounds on the convergence rates of…

Adversarial training, which is to enhance robustness against adversarial attacks, has received much attention because it is easy to generate human-imperceptible perturbations of data to deceive a given deep neural network. In this paper, we…

The use of personal data for training machine learning systems comes with a privacy threat and measuring the level of privacy of a model is one of the major challenges in machine learning today. Identifying training data based on a trained…

The adoption of AI-powered computer vision in industry is often constrained by the need to balance operational utility with worker privacy. Building on our previously proposed privacy-preserving framework, this paper presents its first…

We propose to improve text recognition from a new perspective by separating the text content from complex backgrounds. As vanilla GANs are not sufficiently robust to generate sequence-like characters in natural images, we propose an…

Object detection is an important computer vision task with plenty of real-world applications; therefore, how to enhance its robustness against adversarial attacks has emerged as a crucial issue. However, most of the previous defense methods…

Collaborative machine learning settings like federated learning can be susceptible to adversarial interference and attacks. One class of such attacks is termed model inversion attacks, characterised by the adversary reverse-engineering the…

The surge in multimodal AI's success has sparked concerns over data privacy in vision-and-language tasks. While CLIP has revolutionized multimodal learning through joint training on images and text, its potential to unintentionally disclose…

Sensitivity to adversarial noise hinders deployment of machine learning algorithms in security-critical applications. Although many adversarial defenses have been proposed, robustness to adversarial noise remains an open problem. The most…

Due to the development of machine learning and speech processing, speech emotion recognition has been a popular research topic in recent years. However, the speech data cannot be protected when it is uploaded and processed on servers in the…

Deep neural network-based image compression (NIC) has achieved excellent performance, but NIC method models have been shown to be susceptible to backdoor attacks. Adversarial training has been validated in image compression models as a…

Adversarial training aims to defend against adversaries: malicious opponents whose sole aim is to harm predictive performance in any way possible. This presents a rather harsh perspective, which we assert results in unnecessarily…

Deep learning models are found to be vulnerable to adversarial examples, as wrong predictions can be caused by small perturbation in input for deep learning models. Most of the existing works of adversarial image generation try to achieve…

When data is publicly released for human consumption, it is unclear how to prevent its unauthorized usage for machine learning purposes. Successful model training may be preventable with carefully designed dataset modifications, and we…