paper-with-me

홈 › Papers

Mitigating Downstream Model Risks via Model Provenance

2024-10-03 · Keyu Wang, Abdullah Norozi Iranzad, Scott Schaffter, Meg Risdal, Doina Precup, Jonathan Lebensold

Research and industry are rapidly advancing the innovation and adoption of foundation model-based systems, yet the tools for managing these models have not kept pace. Understanding the provenance and lineage of models is critical for researchers, industry, regulators, and public trust. While model cards and system cards were designed to provide transparency, they fall short in key areas: tracing model genealogy, enabling machine readability, offering reliable centralized management systems, and fostering consistent creation incentives. This challenge mirrors issues in software supply chain security, but AI/ML remains at an earlier stage of maturity. Addressing these gaps requires industry-standard tooling that can be adopted by foundation model publishers, open-source model innovators, and major distribution platforms. We propose a machine-readable model specification format to simplify the creation of model records, thereby reducing error-prone human effort, notably when a new model inherits most of its design from a foundation model. Our solution explicitly traces relationships between upstream and downstream models, enhancing transparency and traceability across the model lifecycle. To facilitate the adoption, we introduce the unified model record (UMR) repository , a semantically versioned system that automates the publication of model records to multiple formats (PDF, HTML, LaTeX) and provides a hosted web interface (https://modelrecord.com/). This proof of concept aims to set a new standard for managing foundation models, bridging the gap between innovation and responsible model management.

📄 PDF Abstract BibTeX arXiv:2410.02230

Code (0)

등록된 구현이 없습니다.

Tasks

Managementmodel

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Mimicking User Data: On Mitigating Fine-Tuning Risks in Closed Large Language Models

2024-06-12 · Francisco Eiras, Aleksandar Petrov, Phillip H. S. Torr, M. Pawan Kumar 외

Fine-tuning large language models on small, high-quality datasets can enhance their performance on specific downstream tasks. Recent research shows that fine-tuning on benign, instruction-following data can inadvertently…

Instruction FollowingSafety Alignment

Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges

2024-09-30 · Qin Liu, Wenjie Mo, Terry Tong, Jiashu Xu 외

The advancement of Large Language Models (LLMs) has significantly impacted various domains, including Web search, healthcare, and software development. However, as these models scale, they become more vulnerable to cyber…

Memorization

Benchmarking Safety Risks of Knowledge-Intensive Reasoning under Malicious Knowledge Editing

2026-05-11 · Qinghua Mao, Xi Lin, Jinze Gu, Jun Wu 외 arxiv

Large language models (LLMs) increasingly rely on knowledge editing to support knowledge-intensive reasoning, but this flexibility also introduces critical safety risks: adversaries can inject malicious or misleading kno…

knowledge editing

Embedding Provenance in Computer Vision Datasets with JSON-LD

2026-03-28 · Lynn Vonderhaar, Timothy Elvira, Tyler Thomas Procko, Omar Ochoa arxiv

With the ubiquity of computer vision in industry, the importance of image provenance is becoming more apparent. Provenance provides information about the origin and derivation of some resource, e.g., an image dataset, en…

Mitigating Provenance-Role Collapse in Long-Term Agents via Typed Memory Representation

2026-05-25 · Zhengda Jin, Bingbing Wang, Jing Li, Ruifeng Xu 외 arxiv

Long-term memory is essential for persistent LLM agents, yet prevailing architectures store historical interactions as unstructured, flat text. This unconstrained storage induces provenance-role collapse, a critical fail…

Answer Generation