Xiaohua Jia
YOU?
Author Swipe
View article: The Potential Application of Exosomes as Therapeutic Agents, Carriers, and Biomarkers in Skin Diseases
The Potential Application of Exosomes as Therapeutic Agents, Carriers, and Biomarkers in Skin Diseases Open
Exosomes, owing to their potent capabilities for intercellular communication, have great potential in modern medicine. The pathogenesis of skin diseases is predominantly characterized by immune imbalance and impaired regenerative processes…
View article: AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin
AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin Open
Large language models (LLMs) are vulnerable to safety risks during fine-tuning, where small amounts of malicious or harmless data can compromise safeguards. In this paper, building on the concept of alignment direction -- defined by the we…
View article: Effects and Mechanisms of Green Manure’s Improvement in Saline-Alkali Soil: A Review
Effects and Mechanisms of Green Manure’s Improvement in Saline-Alkali Soil: A Review Open
Soil salinization is a huge threat to global agricultural productivity, significantly compromising crop development and soil health. In China, the combined pressures of population growth and socioeconomic advancement have progressively dim…
View article: No Query, No Access
No Query, No Access Open
Textual adversarial attacks mislead NLP models, including Large Language Models (LLMs), by subtly modifying text. While effective, existing attacks often require knowledge of the victim model, extensive queries, or access to training data,…
View article: Ginseng exosomes modulate M1/M2 polarisation by activating autophagy and target IKK/IкB/NF-кB to alleviate inflammatory bowel disease
Ginseng exosomes modulate M1/M2 polarisation by activating autophagy and target IKK/IкB/NF-кB to alleviate inflammatory bowel disease Open
In summary, GEs may be a potential treatment for inflammatory bowel disease, and targeting autophagy and macrophage polarisation may help alleviate intestinal inflammation.
View article: Exploring Incremental Unlearning: Techniques, Challenges, and Future Directions
Exploring Incremental Unlearning: Techniques, Challenges, and Future Directions Open
The growing demand for data privacy in Machine Learning (ML) applications has seen Machine Unlearning (MU) emerge as a critical area of research. As the `right to be forgotten' becomes regulated globally, it is increasingly important to de…
View article: CAT: Contrastive Adversarial Training for Evaluating the Robustness of Protective Perturbations in Latent Diffusion Models
CAT: Contrastive Adversarial Training for Evaluating the Robustness of Protective Perturbations in Latent Diffusion Models Open
Latent diffusion models have recently demonstrated superior capabilities in many downstream image synthesis tasks. However, customization of latent diffusion models using unauthorized data can severely compromise the privacy and intellectu…
View article: Protective Perturbations against Unauthorized Data Usage in Diffusion-based Image Generation
Protective Perturbations against Unauthorized Data Usage in Diffusion-based Image Generation Open
Diffusion-based text-to-image models have shown immense potential for various image-related tasks. However, despite their prominence and popularity, customizing these models using unauthorized data also brings serious privacy and intellect…
View article: Embedding Watermarks in Diffusion Process for Model Intellectual Property Protection
Embedding Watermarks in Diffusion Process for Model Intellectual Property Protection Open
In practical application, the widespread deployment of diffusion models often necessitates substantial investment in training. As diffusion models find increasingly diverse applications, concerns about potential misuse highlight the impera…
View article: Multi-Scale Feature Attention Fusion for Image Splicing Forgery Detection
Multi-Scale Feature Attention Fusion for Image Splicing Forgery Detection Open
Image splicing is a widely occurrence image tampering technology. With the rapid development of digital image processing technology, detecting image splicing forgery has become significantly challenging. Although various methods have been …
View article: Training with Differential Privacy: A Gradient-Preserving Noise Reduction Approach with Provable Security
Training with Differential Privacy: A Gradient-Preserving Noise Reduction Approach with Provable Security Open
Deep learning models have been extensively adopted in various regions due to their ability to represent hierarchical features, which highly rely on the training set and procedures. Thus, protecting the training process and deep learning al…
View article: Data‐Driven Design of Triple‐Targeted Protein Nanoprobes for Multiplexed Imaging of Cancer Lymphatic Metastasis
Data‐Driven Design of Triple‐Targeted Protein Nanoprobes for Multiplexed Imaging of Cancer Lymphatic Metastasis Open
Targeted imaging of cancer lymphatic metastasis remains challenging due to its highly heterogeneous molecular and phenotypic diversity. Herein, triple‐targeted protein nanoprobes capable of specifically binding to three targets for imaging…
View article: F <sup>2</sup> Key: Dynamically Converting Your Face into a Private Key Based on COTS Headphones for Reliable Voice Interaction
F <sup>2</sup> Key: Dynamically Converting Your Face into a Private Key Based on COTS Headphones for Reliable Voice Interaction Open
In this paper, we proposed F2Key, the first earable physical security system based on commercial off-the-shelf headphones. F2Key enables impactful applications, such as enhancing voiceprint-based authentication systems, reliable voice assi…
View article: Machine Unlearning: Solutions and Challenges
Machine Unlearning: Solutions and Challenges Open
Machine learning models may inadvertently memorize sensitive, unauthorized, or malicious data, posing risks of privacy breaches, security vulnerabilities, and performance degradation. To address these issues, machine unlearning has emerged…
View article: Guest Editorial Special Issue on Recent Advances of Security, Privacy, and Trust in Mobile Crowdsourcing
Guest Editorial Special Issue on Recent Advances of Security, Privacy, and Trust in Mobile Crowdsourcing Open
With the rapid advances in mobile and communication technologies, mobile devices are equipped with powerful processors, various sensors, large memories, and fast wireless communication modules. By taking advantage of powerful mobile device…
View article: Machine Unlearning: Solutions and Challenges
Machine Unlearning: Solutions and Challenges Open
Machine learning models may inadvertently memorize sensitive, unauthorized, or malicious data, posing risks of privacy breaches, security vulnerabilities, and performance degradation. To address these issues, machine unlearning has emerged…
View article: On the Security Bootstrapping in Named Data Networking
On the Security Bootstrapping in Named Data Networking Open
By requiring all data packets been cryptographically authenticatable, the Named Data Networking (NDN) architecture design provides a basic building block for secured networking. This basic NDN function requires that all entities in an NDN …
View article: A truthful dynamic combinatorial double auction model for cloud resource allocation
A truthful dynamic combinatorial double auction model for cloud resource allocation Open
Dynamic auction-based resource allocation models require little global price information, are decentralized and suitable for the distributed systems like cloud computing. For the cloud computing market, we proposed a Truthful Dynamic Combi…
View article: Welcome Message
Welcome Message Open
It is our great pleasure to welcome you to the 43rd edition of the IEEE International Conference on Distributed Computing Systems (ICDCS), held in Hong Kong on July 18-21, 2023. This conference series fosters novel and exciting research in…
View article: Intellectual Property Protection of Diffusion Models via the Watermark Diffusion Process
Intellectual Property Protection of Diffusion Models via the Watermark Diffusion Process Open
Diffusion models have rapidly become a vital part of deep generative architectures, given today's increasing demands. Obtaining large, high-performance diffusion models demands significant resources, highlighting their importance as intell…