10 papers
Label-Budgeted Attribute Inference from Protected Features in Edge-Cloud Split Multimodal LLMs
Junguang Yao, Peichun Hua, Hanxiu Zhang +1
Edge-cloud split inference runs the early layers of a multimodal large language model (MLLM) on a device and sends intermediate features to a server to complete the task. While kee…
Relevance Is Not Sufficient Evidence: Detecting Evidence Gaps Before Generation in RAG
Suting Chen, Peichun Hua, Yunming Xiao
Retrieval-augmented generation (RAG) grounds large language models in external sources, but retrieved passages often name the right entities without providing the facts needed to a…
Backdoor in the Loop: Compromising Agentic Search via Malicious Retrievers
Beining Xu, Peichun Hua, Yunming Xiao
Agentic retrieval-augmented generation (RAG) interleaves reasoning with repeated retrieval, giving the retriever influence over both the evidence an agent observes and its subseque…
Semantics Delivery Network: Rethinking Web Retrieval Infrastructure for LLM Agents
Peichun Hua, Yunming Xiao
Large language models (LLMs) increasingly ground their answers in proprietary data and live web content through both single-shot retrieval-augmented generation (RAG) and multi-turn…
Matryoshka Hash Representations for Model-Aware Compact Semantic Retrieval
Peichun Hua, Yunming Xiao
Retrieval-augmented generation (RAG) depends on dense retrieval: each document is stored as a learned vector, and a query is answered by finding its nearest neighbors in that vecto…
Spruce: Scalable Private Outsourced Retrieval Using Compact Embeddings
Peichun Hua, Yunming Xiao
Retrieval-Augmented Generation (RAG) has made dense retrieval over large document collections a standard building block. Organizations increasingly outsource vector indexes to untr…
Pointing the Way, Hiding the Destination: Practical Private Dense Retrieval at Scale
Peichun Hua, Danyang Chen, Junan Zhang +5
Hosted retrieval-augmented generation (RAG) and semantic search allow users to query valuable provider-held corpora, raising two competing demands: to hide each query and chosen re…
Behavioral Skill Reconstruction: Reconstructing Hidden Functionality from LLM Agent Skills
Peichun Hua, Haoxuan Xu, Mengyuan Li
Closed source agent skills may encode proprietary instructions, scripts, constants, and data. Providers may offer their capabilities as services while keeping the underlying packag…
A Unified Open-Set Framework for Scalable PUF-Based Authentication of Heterogeneous IoT Devices
Xin Wang, Peichun Hua, Chip Hong Chang +2
As modern cyber systems scale to include large populations of heterogeneous IoT devices, securing them against impersonation and forgery is a critical cybersecurity challenge. Phys…
Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring
Peichun Hua, Hao Li, Shanghao Shi +2
Large Vision-Language Models (LVLMs) are vulnerable to a growing array of multimodal jailbreak attacks, necessitating defenses that are both generalizable to novel threats and effi…