Related papers: Adversary-Aware Private Inference over Wireless Ch…
Self-evolving agentic artificial intelligence (AI) offers a new paradigm for future wireless systems by enabling autonomous agents to continually adapt and improve without human intervention. Unlike static AI models, self-evolving agents…
Self-attention heads are characteristic of Transformer models and have been well studied for interpretability and pruning. In this work, we demonstrate an altogether different utility of attention heads, namely for adversarial detection.…
Data privacy is an increasingly important aspect of many real-world Data sources that contain sensitive information may have immense potential which could be unlocked using the right privacy enhancing transformations, but current methods…
Many assumptions that underpin human concepts of identity do not hold for machine minds that can be copied, edited, or simulated. We argue that there exist many different coherent identity boundaries (e.g.\ instance, model, persona), and…
Deep learning models deployed on edge devices are increasingly used in safety-critical applications. However, their vulnerability to adversarial perturbations poses significant risks, especially in Federated Learning (FL) settings where…
Personal devices are omnipresent in our lives, seamlessly monitoring our activities, from smart rings tracking sleep patterns to smartwatches keeping an eye on missed heartbeats. The rich data streams from such devices fuel advanced…
When applying machine learning to sensitive data, one has to find a balance between accuracy, information security, and computational-complexity. Recent studies combined Homomorphic Encryption with neural networks to make inferences while…
Generative adversarial networks (GANs) have been successfully applied to transfer visual attributes in many domains, including that of human face images. This success is partly attributable to the facts that human faces have similar shapes…
Next-generation wireless networks like 5G promise faster speed, shorter latency, and the ability to connect more devices. Such benefits are set to make drastic changes to the future society, empowering smart cities, enabling autonomous…
Memorization in large-scale text-to-image diffusion models poses significant security and intellectual property risks, enabling adversarial attribute extraction and the unauthorized reproduction of sensitive or proprietary features. While…
Deep learning has been widely applied in many computer vision applications, with remarkable success. However, running deep learning models on mobile devices is generally challenging due to the limitation of computing resources. A popular…
With the increasing deployment of intelligent sensing technologies in highly sensitive environments such as restrooms and locker rooms, visual surveillance systems face a profound privacy-security paradox. Existing privacy-preserving…
The proliferation of AI agents, with their complex and context-dependent actions, renders conventional privacy paradigms obsolete. This position paper argues that the current model of privacy management, rooted in a user's unilateral…
Deep learning technologies are pivotal in enhancing the performance of WiFi-based wireless sensing systems. However, they are inherently vulnerable to adversarial perturbation attacks, and regrettably, there is lacking serious attention to…
Transferability of adversarial examples is of central importance for attacking an unknown model, which facilitates adversarial attacks in more practical scenarios, e.g., black-box attacks. Existing transferable attacks tend to craft…
This paper focuses on discrete-time wireless sensor networks with privacy-preservation. In practical applications, information exchange between sensors is subject to attacks. For the information leakage caused by the attack during the…
Network traffic analysis using AI (machine learning and deep learning) models made significant progress over the past decades. Traffic analysis addresses various challenging problems in network security, ranging from detection of anomalies…
Object detection networks have reached an impressive performance level, yet a lack of suitable data in specific applications often limits it in practice. Typically, additional data sources are utilized to support the training task. In…
In the realm of multimedia data analysis, the extensive use of image datasets has escalated concerns over privacy protection within such data. Current research predominantly focuses on privacy protection either in data sharing or upon the…
Differentially private wireless federated learning (DPWFL) is a promising framework for protecting sensitive user data. However, foundational questions on how to precisely characterize privacy loss remain open, and existing work is further…