9 papers
CoreGuard: Safeguarding Foundational Capabilities of LLMs Against Model Stealing in Edge Deployment
Qinfeng Li, Tianyue Luo, Xuhong Zhang +8
Proprietary large language models (LLMs) exhibit strong generalization capabilities across diverse tasks and are increasingly deployed on edge devices for efficiency and privacy re…
Scalable Multi-Stage Influence Function for Large Language Models via Eigenvalue-Corrected Kronecker-Factored Parameterization
Yuntai Bao, Xuhong Zhang, Tianyu Du +4
Pre-trained large language models (LLMs) are commonly fine-tuned to adapt to downstream tasks. Since the majority of knowledge is acquired during pre-training, attributing the pred…
HogVul: Black-box Adversarial Code Generation Framework Against LM-based Vulnerability Detectors
Jingxiao Yang, Ping He, Tianyu Du +2
Recent advances in software vulnerability detection have been driven by Language Model (LM)-based approaches. However, these models remain vulnerable to adversarial attacks that ex…
CLMTracing: Black-box User-level Watermarking for Code Language Model Tracing
Boyu Zhang, Ping He, Tianyu Du +4
With the widespread adoption of open-source code language models (code LMs), intellectual property (IP) protection has become an increasingly critical concern. While current waterm…
Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding
Yanming Liu, Xinyue Peng, Jiannan Cao +6
Large language models (LLMs) have shown remarkable capabilities in natural language processing; however, they still face difficulties when tasked with understanding lengthy context…
Tool-Planner: Task Planning with Clusters across Multiple Tools
Yanming Liu, Xinyue Peng, Jiannan Cao +6
Large language models (LLMs) have demonstrated exceptional reasoning capabilities, enabling them to solve various complex problems. Recently, this ability has been applied to the p…