Jing Shang (Beijing Jiaotong University), Jian Wang (Beijing Jiaotong University), Kailun Wang (Beijing Jiaotong University), Jiqiang Liu (Beijing Jiaotong University), Nan Jiang (Beijing University of Technology), Md Armanuzzaman (Northeastern University), Ziming Zhao (Northeastern University)

Model pruning is a technique for compressing deep learning models, and using an iterative way to prune the model can achieve better compression effects with lower utility loss. However, our analysis reveals that iterative pruning significantly increases model memorization, making the pruned models more vulnerable to membership inference attacks (MIAs). Unfortunately, the vast majority of existing defenses against MIAs are designed for original and unpruned models. In this paper, we propose a new framework WeMem to weaken memorization in the iterative pruning process. Specifically, our analysis identifies two important factors that increase memorization in iterative pruning, namely data reuse and inherent memorability. We consider the individual and combined impacts of both factors, forming three scenarios that lead to increased memorization in iteratively pruned models. We design three defense primitives based on these factors' characteristics. By combining these primitives, we propose methods tailored to each scenario to weaken memorization effectively. Comprehensive experiments under ten adaptive MIAs demonstrate the effectiveness of the proposed defenses. Moreover, our defenses outperform five existing defenses in terms of privacy-utility tradeoff and efficiency. Additionally, we enhance the proposed defenses to automatically adjust settings for optimal defense, improving their practicability.

View More Papers

Scale-MIA: A Scalable Model Inversion Attack against Secure Federated...

Shanghao Shi (Virginia Tech), Ning Wang (University of South Florida), Yang Xiao (University of Kentucky), Chaoyu Zhang (Virginia Tech), Yi Shi (Virginia Tech), Y. Thomas Hou (Virginia Polytechnic Institute and State University), Wenjing Lou (Virginia Polytechnic Institute and State University)

Read More

Securing BGP ASAP: ASPA and other Post-ROV Defenses

Justin Furuness (University of Connecticut), Cameron Morris (University of Connecticut), Reynaldo Morillo (University of Connecticut), Arvind Kasiliya (University of Connecticut), Bing Wang (University of Connecticut), Amir Herzberg (University of Connecticut)

Read More

Privacy-Preserving Data Deduplication for Enhancing Federated Learning of Language...

Aydin Abadi (Newcastle University), Vishnu Asutosh Dasu (Pennsylvania State University), Sumanta Sarkar (University of Warwick)

Read More

Ctrl+Alt+Deceive: Quantifying User Exposure to Online Scams

Platon Kotzias (Norton Research Group, BforeAI), Michalis Pachilakis (Norton Research Group, Computer Science Department University of Crete), Javier Aldana Iuit (Norton Research Group), Juan Caballero (IMDEA Software Institute), Iskander Sanchez-Rola (Norton Research Group), Leyla Bilge (Norton Research Group)

Read More