Memorization in deep learning: A survey

• URL: http://arxiv.org/abs/2406.03880v1
• Date: Thu, 6 Jun 2024 09:17:40 GMT
• Title: Memorization in deep learning: A survey
• Authors: Jiaheng Wei, Yanjun Zhang, Leo Yu Zhang, Ming Ding, Chao Chen, Kok-Leong Ong, Jun Zhang, Yang Xiang,
• Abstract summary: Recent investigations have uncovered an interesting phenomenon in which Deep Neural Networks (DNNs) tend to memorize specific details from examples rather than learning general patterns. This raises critical questions about the nature of generalization in DNNs and their susceptibility to security breaches. We present a systematic framework to organize memorization definitions based on the generalization and security/privacy domains.
• Score: 26.702878179026754
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep Learning (DL) powered by Deep Neural Networks (DNNs) has revolutionized various domains, yet understanding the intricacies of DNN decision-making and learning processes remains a significant challenge. Recent investigations have uncovered an interesting memorization phenomenon in which DNNs tend to memorize specific details from examples rather than learning general patterns, affecting model generalization, security, and privacy. This raises critical questions about the nature of generalization in DNNs and their susceptibility to security breaches. In this survey, we present a systematic framework to organize memorization definitions based on the generalization and security/privacy domains and summarize memorization evaluation methods at both the example and model levels. Through a comprehensive literature review, we explore DNN memorization behaviors and their impacts on security and privacy. We also introduce privacy vulnerabilities caused by memorization and the phenomenon of forgetting and explore its connection with memorization. Furthermore, we spotlight various applications leveraging memorization and forgetting mechanisms, including noisy label learning, privacy preservation, and model enhancement. This survey offers the first-in-kind understanding of memorization in DNNs, providing insights into its challenges and opportunities for enhancing AI development while addressing critical ethical concerns.

Related papers

• The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation [97.0658685969199]
  Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet they also exhibit memorization of their training data.<n>This paper synthesizes recent studies and investigates the landscape of memorization, the factors influencing it, and methods for its detection and mitigation.
  arXiv  Detail & Related papers  (2025-07-08T01:30:46Z)
• In Praise of Stubbornness: The Case for Cognitive-Dissonance-Aware Knowledge Updates in LLMs [12.126745558519737]
  Large language models (LLMs) struggle to continually update their knowledge without catastrophic forgetting. Humans effortlessly integrate new information, detect conflicts with existing beliefs, and selectively update their mental models. This paper introduces a cognitive-inspired investigation paradigm to study continual knowledge updating in LLMs.
  arXiv  Detail & Related papers  (2025-02-05T23:49:33Z)
• Open Problems in Machine Unlearning for AI Safety [61.43515658834902]
  Machine unlearning -- the ability to selectively forget or suppress specific types of knowledge -- has shown promise for privacy and data removal tasks. In this paper, we identify key limitations that prevent unlearning from serving as a comprehensive solution for AI safety.
  arXiv  Detail & Related papers  (2025-01-09T03:59:10Z)
• Privacy in Fine-tuning Large Language Models: Attacks, Defenses, and Future Directions [11.338466798715906]
  Fine-tuning Large Language Models (LLMs) can achieve state-of-the-art performance across various domains. This paper provides a comprehensive survey of privacy challenges associated with fine-tuning LLMs. We highlight vulnerabilities to various privacy attacks, including membership inference, data extraction, and backdoor attacks.
  arXiv  Detail & Related papers  (2024-12-21T06:41:29Z)
• Model Inversion Attacks: A Survey of Approaches and Countermeasures [59.986922963781]
  Recently, a new type of privacy attack, the model inversion attacks (MIAs), aims to extract sensitive features of private data for training. Despite the significance, there is a lack of systematic studies that provide a comprehensive overview and deeper insights into MIAs. This survey aims to summarize up-to-date MIA methods in both attacks and defenses.
  arXiv  Detail & Related papers  (2024-11-15T08:09:28Z)
• Undesirable Memorization in Large Language Models: A Survey [5.659933808910005]
  We present a Systematization of Knowledge (SoK) on the topic of memorization in Large Language Models (LLMs) Memorization is the effect that a model tends to store and reproduce phrases or passages from the training data. We discuss the metrics and methods used to measure memorization, followed by an analysis of the factors that contribute to memorization phenomenon.
  arXiv  Detail & Related papers  (2024-10-03T16:34:46Z)
• Adversarial Challenges in Network Intrusion Detection Systems: Research Insights and Future Prospects [0.33554367023486936]
  This paper provides a comprehensive review of machine learning-based Network Intrusion Detection Systems (NIDS) We critically examine existing research in NIDS, highlighting key trends, strengths, and limitations. We discuss emerging challenges in the field and offer insights for the development of more robust and resilient NIDS.
  arXiv  Detail & Related papers  (2024-09-27T13:27:29Z)
• Preserving Privacy in Large Language Models: A Survey on Current Threats and Solutions [12.451936012379319]
  Large Language Models (LLMs) represent a significant advancement in artificial intelligence, finding applications across various domains. Their reliance on massive internet-sourced datasets for training brings notable privacy issues. Certain application-specific scenarios may require fine-tuning these models on private data.
  arXiv  Detail & Related papers  (2024-08-10T05:41:19Z)
• A Comprehensive Study of Knowledge Editing for Large Language Models [82.65729336401027]
  Large Language Models (LLMs) have shown extraordinary capabilities in understanding and generating text that closely mirrors human communication. This paper defines the knowledge editing problem and provides a comprehensive review of cutting-edge approaches. We introduce a new benchmark, KnowEdit, for a comprehensive empirical evaluation of representative knowledge editing approaches.
  arXiv  Detail & Related papers  (2024-01-02T16:54:58Z)
• Exploring Memorization in Fine-tuned Language Models [53.52403444655213]
  We conduct the first comprehensive analysis to explore language models' memorization during fine-tuning across tasks. Our studies with open-sourced and our own fine-tuned LMs across various tasks indicate that memorization presents a strong disparity among different fine-tuning tasks. We provide an intuitive explanation of this task disparity via sparse coding theory and unveil a strong correlation between memorization and attention score distribution.
  arXiv  Detail & Related papers  (2023-10-10T15:41:26Z)
• A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning [58.107474025048866]
  Forgetting refers to the loss or deterioration of previously acquired knowledge. Forgetting is a prevalent phenomenon observed in various other research domains within deep learning.
  arXiv  Detail & Related papers  (2023-07-16T16:27:58Z)
• New Challenges in Reinforcement Learning: A Survey of Security and Privacy [26.706957408693363]
  Reinforcement learning (RL) is one of the most important branches of AI. RL has been widely applied in multiple areas, such as healthcare, data markets, autonomous driving, and robotics. Some of these applications and systems have been shown to be vulnerable to security or privacy attacks.
  arXiv  Detail & Related papers  (2022-12-31T12:30:43Z)
• Measures of Information Reflect Memorization Patterns [53.71420125627608]
  We show that the diversity in the activation patterns of different neurons is reflective of model generalization and memorization. Importantly, we discover that information organization points to the two forms of memorization, even for neural activations computed on unlabelled in-distribution examples.
  arXiv  Detail & Related papers  (2022-10-17T20:15:24Z)
• Privacy and Robustness in Federated Learning: Attacks and Defenses [74.62641494122988]
  We conduct the first comprehensive survey on this topic. Through a concise introduction to the concept of FL, and a unique taxonomy covering: 1) threat models; 2) poisoning attacks and defenses against robustness; 3) inference attacks and defenses against privacy, we provide an accessible review of this important topic.
  arXiv  Detail & Related papers  (2020-12-07T12:11:45Z)
• Privacy in Deep Learning: A Survey [16.278779275923448]
  The ever-growing advances of deep learning in many areas have led to the adoption of Deep Neural Networks (DNNs) in production systems. The availability of large datasets and high computational power are the main contributors to these advances. This poses serious privacy concerns as this data can be misused or leaked through various vulnerabilities.
  arXiv  Detail & Related papers  (2020-04-25T23:47:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.