13 papers
VeriPort: Automated and Verified Patch Backporting at Scale
Jonah Ghebremichael, Wenxin Jiang, Mikola Lysenko +3
One of the key challenges for securing the software supply chain is addressing known vulnerabilities in third-party open-source dependencies. Security patches are frequently only a…
Debiasing LLMs by Fine-tuning
Zhenyu Gao, Wenxi Jiang, Yutong Yan
Prior research shows that large language models (LLMs) exhibit systematic extrapolation bias when forming predictions from both experimental and real-world data, and that prompt-ba…
DatedGPT: Preventing Lookahead Bias in Large Language Models with Time-Aware Pretraining
Yutong Yan, Raphael Tang, Zhenyu Gao +2
Large language models pretrained on internet-scale data risk lookahead bias in forecasting tasks, as they may have already seen the true outcome during training. To address this, w…
AgentHub: A Registry for Discoverable, Verifiable, and Reproducible AI Agents
Erik Pautsch, Tanmay Singla, Parv Kumar +6
LLM-based agents are rapidly proliferating, yet the infrastructure for discovering, evaluating, and governing them remains fragmented compared to mature ecosystems like software pa…
PickleBall: Secure Deserialization of Pickle-based Machine Learning Models (Extended Report)
Andreas D. Kellas, Neophytos Christou, Wenxin Jiang +6
Machine learning model repositories such as the Hugging Face Model Hub facilitate model exchanges. However, bad actors can deliver malware through compromised models. Existing defe…
"I see models being a whole other thing": An Empirical Study of Pre-Trained Model Naming Conventions and A Tool for Enhancing Naming Consistency
Wenxin Jiang, Mingyu Kim, Chingwo Cheung +3
As innovation in deep learning continues, many engineers are incorporating Pre-Trained Models (PTMs) as components in computer systems. Some PTMs are foundation models, and others…