4 papers
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…
Software Dependencies 2.0: An Empirical Study of Reuse and Integration of Pre-Trained Models in Open-Source Projects
Jerin Yasmin, Wenxin Jiang, James C. Davis +1
Pre-trained models (PTMs) are machine learning models that have been trained in advance, often on large-scale data, and can be reused for new tasks, thereby reducing the need for c…
ConfuGuard: Using Metadata to Detect Active and Stealthy Package Confusion Attacks Accurately and at Scale
Wenxin Jiang, Berk Çakar, Mikola Lysenko +1
Package confusion attacks such as typosquatting threaten software supply chains. Attackers make packages with names that syntactically or semantically resemble legitimate ones, tri…
A Partial Replication of MaskFormer in TensorFlow on TPUs for the TensorFlow Model Garden
Vishal Purohit, Wenxin Jiang, Akshath R. Ravikiran +1
This paper undertakes the task of replicating the MaskFormer model a universal image segmentation model originally developed using the PyTorch framework, within the TensorFlow ecos…