Cover Image

Mitigating Downstream Model Risks via Model Provenance

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Keyu, Iranzad, Abdullah Norozi, Schaffter, Scott, Risdal, Meg, Precup, Doina, Lebensold, Jonathan
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

On the Privacy of Selection Mechanisms with Gaussian Noise
by: Lebensold, Jonathan, et al.
Published: (2024)

Attacking Attention of Foundation Models Disrupts Downstream Tasks
by: Silva, Hondamunige Prasanna, et al.
Published: (2025)

Explaining the Model, Protecting Your Data: Revealing and Mitigating the Data Privacy Risks of Post-Hoc Model Explanations via Membership Inference
by: Huang, Catherine, et al.
Published: (2024)

Adversarial Attacks on Downstream Weather Forecasting Models: Application to Tropical Cyclone Trajectory Prediction
by: Deng, Yue, et al.
Published: (2025)

Model Provenance Testing for Large Language Models
by: Nikolic, Ivica, et al.
Published: (2025)

How to Enhance Downstream Adversarial Robustness (almost) without Touching the Pre-Trained Foundation Model?
by: Liu, Meiqi, et al.
Published: (2025)

DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning
by: Lebensold, Jonathan, et al.
Published: (2024)

Learning to Poison Large Language Models for Downstream Manipulation
by: Zhou, Xiangyu, et al.
Published: (2024)

Secure Transfer Learning: Training Clean Models Against Backdoor in (Both) Pre-trained Encoders and Downstream Datasets
by: Zhang, Yechao, et al.
Published: (2025)

TREC: APT Tactic / Technique Recognition via Few-Shot Provenance Subgraph Learning
by: Lv, Mingqi, et al.
Published: (2024)

Jailbreaking and Mitigation of Vulnerabilities in Large Language Models
by: Peng, Benji, et al.
Published: (2024)

DeepProv: Behavioral Characterization and Repair of Neural Networks via Inference Provenance Graph Analysis
by: Hmida, Firas Ben, et al.
Published: (2025)

Randomization Techniques to Mitigate the Risk of Copyright Infringement
by: Chen, Wei-Ning, et al.
Published: (2024)

Pre-trained Encoder Inference: Revealing Upstream Encoders In Downstream Machine Learning Services
by: Fu, Shaopeng, et al.
Published: (2024)

Enhancing Data Provenance and Model Transparency in Federated Learning Systems -- A Database Approach
by: Gu, Michael, et al.
Published: (2024)

Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace
by: Yang, Jinluan, et al.
Published: (2024)

Self-Purification Mitigates Backdoors in Multimodal Diffusion Language Models
by: Wan, Guangnian, et al.
Published: (2026)

Interpreting GNN-based IDS Detections Using Provenance Graph Structural Features
by: Mukherjee, Kunal, et al.
Published: (2023)

AUTOLYCUS: Exploiting Explainable AI (XAI) for Model Extraction Attacks against Interpretable Models
by: Oksuz, Abdullah Caglar, et al.
Published: (2023)

PIDSMaker: Building and Evaluating Provenance-based Intrusion Detection Systems
by: Bilot, Tristan, et al.
Published: (2026)

Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss
by: Liu, Zhenlong, et al.
Published: (2024)

threaTrace: Detecting and Tracing Host-based Threats in Node Level Through Provenance Graph Learning
by: Wang, Su, et al.
Published: (2021)

ZKPROV: A Zero-Knowledge Approach to Dataset Provenance for Large Language Models
by: Namazi, Mina, et al.
Published: (2025)

An End-to-End Framework for Functionality-Embedded Provenance Graph Construction and Threat Interpretation
by: Ghosh, Kushankur, et al.
Published: (2026)

Diff-Cleanse: Identifying and Mitigating Backdoor Attacks in Diffusion Models
by: Hao, Jiang, et al.
Published: (2024)

Improved Algorithms for Differentially Private Language Model Alignment
by: Chen, Keyu, et al.
Published: (2025)

LoMime: Query-Efficient Membership Inference using Model Extraction in Label-Only Settings
by: Oksuz, Abdullah Caglar, et al.
Published: (2026)

Transferable Adversarial Attacks on SAM and Its Downstream Models
by: Xia, Song, et al.
Published: (2024)

Mitigating Noise Detriment in Differentially Private Federated Learning with Model Pre-training
by: Jin, Huitong, et al.
Published: (2024)

Defeating Cerberus: Concept-Guided Privacy-Leakage Mitigation in Multimodal Language Models
by: Zhang, Boyang, et al.
Published: (2025)

A Formal Framework for Assessing and Mitigating Emergent Security Risks in Generative AI Models: Bridging Theory and Dynamic Risk Mitigation
by: Srivastava, Aviral, et al.
Published: (2024)

Data Plagiarism Index: Characterizing the Privacy Risk of Data-Copying in Tabular Generative Models
by: Ward, Joshua, et al.
Published: (2024)

Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk
by: Li, Zhangheng, et al.
Published: (2024)

Fusing Pruned and Backdoored Models: Optimal Transport-based Data-free Backdoor Mitigation
by: Lin, Weilin, et al.
Published: (2024)

TRYLOCK: Defense-in-Depth Against LLM Jailbreaks via Layered Preference and Representation Engineering
by: Thornton, Scott
Published: (2026)

Differentially Private Federated $k$-Means Clustering with Server-Side Data
by: Scott, Jonathan, et al.
Published: (2025)

Mitigating Watermark Forgery in Generative Models via Randomized Key Selection
by: Aremu, Toluwani, et al.
Published: (2025)

Watermarking Language Models through Language Models
by: Dasgupta, Agnibh, et al.
Published: (2024)

Stealix: Model Stealing via Prompt Evolution
by: Zhuang, Zhixiong, et al.
Published: (2025)

AMCR: A Framework for Assessing and Mitigating Copyright Risks in Generative Models
by: Yin, Zhipeng, et al.
Published: (2025)