6 papers
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…
RADS-Checker: Measuring Compliance with Right of Access by the Data Subject in Android Markets
Zhenhua Li, Zhanpeng Liang, Congcong Yao +2
The latest data protection regulations worldwide, such as the General Data Protection Regulation (GDPR), have established the Right of Access by the Data Subject (RADS), granting u…