相关论文: Safeguarding LLM Embeddings in End-Cloud Collabora…

The adoption of Large Language Models (LLMs) has revolutionized AI applications but poses significant challenges in safeguarding user privacy. Ensuring compliance with privacy regulations such as GDPR and CCPA while addressing nuanced…

An increasing number of companies have begun providing services that leverage cloud-based large language models (LLMs), such as ChatGPT. However, this development raises substantial privacy concerns, as users' prompts are transmitted to and…

Large Language Models (LLMs) are increasingly deployed for code generation in high-stakes software development, yet their limited transparency in security reasoning and brittleness to evolving vulnerability patterns raise critical…

Safety backdoor attacks in large language models (LLMs) enable the stealthy triggering of unsafe behaviors while evading detection during normal interactions. The high dimensionality of potential triggers in the token space and the diverse…

As LLMs become increasingly capable, editorial boards and program committees are growing concerned about reviewers who fully outsource peer review to commercial chatbots. This concern stems from prior findings that current chatbots lack the…

Large language models (LLMs) have significantly transformed natural language understanding and generation, but they raise privacy concerns due to potential exposure of sensitive information. Studies have highlighted the risk of information…

In today's data-driven analytics landscape, deep learning has become a powerful tool, with latent representations, known as embeddings, playing a central role in several applications. In the face analytics domain, such embeddings are…

With the increasing use of cloud-based services for training and deploying machine learning models, data privacy has become a major concern. This is particularly important for natural language processing (NLP) models, which often process…

Logit-based LLM watermarking traces and verifies AI-generated content by maintaining green and red token lists and increasing the likelihood of green tokens during generation. However, it fails in low-entropy scenarios, where predictable…

We propose a privacy-preserving ensemble infused enhanced Deep Neural Network (DNN) based learning framework in this paper for Internet-of-Things (IoT), edge, and cloud convergence in the context of healthcare. In the convergence, edge…

Privacy Preserving Data Mining (PPDM) addresses the problem of developing accurate models about aggregated data without access to precise information in individual data record. A widely studied \emph{perturbation-based PPDM} approach…

Objective: Applying large language models (LLMs) to the clinical domain is challenging due to the context-heavy nature of processing medical records. Retrieval-augmented generation (RAG) offers a solution by facilitating reasoning over…

The memorization of training data in large language models (LLMs) poses significant privacy and copyright concerns. Existing data extraction methods, particularly heuristic-based divergence attacks, often exhibit limited success and offer…

Recent work shows that sensitive user data can be reconstructed from gradient updates, breaking the key privacy promise of federated learning. While success was demonstrated primarily on image data, these methods do not directly transfer to…

Adapter-based Federated Large Language Models (FedLLMs) are widely adopted to reduce the computational, storage, and communication overhead of full-parameter fine-tuning for web-scale applications while preserving user privacy. By freezing…

Text data are often encoded as dense vectors, known as embeddings, which capture semantic, syntactic, contextual, and domain-specific information. These embeddings, widely adopted in various applications, inherently contain rich information…

Large Language Models (LLMs) that can be deployed locally have recently gained popularity for privacy-sensitive tasks, with companies such as Meta, Google, and Intel playing significant roles in their development. However, the security of…

The interactive nature of Large Language Models (LLMs), which closely track user data and context, has prompted users to share personal and private information in unprecedented ways. Even when users opt out of allowing their data to be used…

As LLM-powered agents are increasingly deployed in edge-cloud environments, personalized memory has become a key enabler of long-term adaptation and user-centric interaction. However, cloud-assisted memory management exposes sensitive user…

Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks. However, this communication also creates an attack surface where malicious…