8 papers
CircuitBreak: Pruning a Sparse Safety Circuit of Neurons
Jincheng Ying, Li Wenlin, Wencheng Yang +1
White-box neuron pruning has shown that refusal in large language models (LLMs) can depend on a small, removable set of feed-forward (FFN) channels. Existing attacks either need ca…
Mask2Shield: Strengthening LLM Safety against Neuron-Pruning Attacks
Ying JinCheng, Minghui Xu, Yinhao Xiao +2
Large language models (LLMs) are safety-aligned before deployment to reduce harmful content generation. Yet neuron-level pruning attacks show that refusal can depend on a small set…
Bridging Diffusion Pruning and Step Distillation with Teacher-Aligned Repair
Jincheng Ying, Li Wenlin, Minghui Xu +1
Diffusion models generate high-quality images, but their inference cost comes from two sources: large denoising networks and repeated denoising steps. Existing compression pipeline…
GeoContra: From Fluent GIS Code to Verifiable Spatial Analysis with Geography-Grounded Repair
Yinhao Xiao, Rongbo Xiao, Yihan Zhang
Reliable spatial analysis in GIScience requires preserving coordinate semantics, topology, units, and geographic plausibility. Current LLM-based GIS systems generate fluent scripts…
Efficient Diffusion Distillation via Embedding Loss
Jincheng Ying, Yitao Chen, Li Wenlin +2
Recent advances in distilling expensive diffusion models into efficient few-step generators show significant promise. However, these methods typically demand substantial computatio…
EvoPatch-IoT: Evolution-Aware Cross-Architecture Vulnerability Retrieval and Patch-State Profiling for BusyBox-Based IoT Firmware
Yinhao Xiao, Huixi Li, Yongluo Shen
BusyBox is one of the most widely reused userland components in Linux-based Internet-of-Things (IoT) firmware, yet its security assessment remains difficult because firmware images…
HWE-Bench: Can Language Models Perform Board-level Schematic Designs?
Weibo Qiu, Yinhao Xiao, Runyu Pan
Large Language Models (LLMs) have demonstrated significant potential in various engineering tasks, including software development, digital logic generation, and companion document…
Low Rank Comes with Low Security: Gradient Assembly Poisoning Attacks against Distributed LoRA-based LLM Systems
Yueyan Dong, Minghui Xu, Qin Hu +5
Low-Rank Adaptation (LoRA) has become a popular solution for fine-tuning large language models (LLMs) in federated settings, dramatically reducing update costs by introducing train…