7 papers
Mitigating Database Leakage in RAG Systems with Keyword-Grounded Fact Substitution
Ziliang Zhang, Yubo Zhu, Wei Tong +4
Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm for combining large language models (LLMs) with external knowledge sources. However, RAG systems remain vuln…
PURPOSE: Poisoning Conflict Resolution in RAG via Proxy-Fact-Grounded Updates
Zijian Wang, Yubo Zhu, Muzhi Dong +7
In Retrieval-Augmented Generation (RAG), post-retrieval conflict resolution arbitrates among noisy or contradictory retrieved passages. However, the robustness of this safeguard ag…
Secret Stealing Attacks on Local LLM Fine-Tuning through Supply-Chain Model Code Backdoors
Zi Li, Tian Zhou, Wenze Li +3
Local fine-tuning datasets routinely contain sensitive secrets such as API keys, personal identifiers, and financial records. Although ''local offline fine-tuning'' is often viewed…
Distillability of LLM Security Logic: Predicting Attack Success Rate of Outline Filling Attack via Ranking Regression
Tianyu Zhang, Zihang Xi, Jingyu Hua +1
In the realm of black-box jailbreak attacks on large language models (LLMs), the feasibility of constructing a narrow safety proxy, a lightweight model designed to predict the atta…
CoDefend: Cross-Modal Collaborative Defense via Diffusion Purification and Prompt Optimization
Fengling Zhu, Boshi Liu, Jingyu Hua +1
Multimodal Large Language Models (MLLMs) have achieved remarkable success in tasks such as image captioning, visual question answering, and cross-modal reasoning by integrating vis…
OFL: Opportunistic Federated Learning for Resource-Heterogeneous and Privacy-Aware Devices
Yunlong Mao, Mingyang Niu, Ziqin Dang +7
Efficient and secure federated learning (FL) is a critical challenge for resource-limited devices, especially mobile devices. Existing secure FL solutions commonly incur significan…