The paper "Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses" provides a comprehensive review of model inversion (MI) attacks that exploit trained deep neural networks to reconstruct private training data. It traces the evolution of MI from early machine‑learning contexts to recent DNN‑based attacks across various modalities and learning tasks, offering a detailed taxonomy and comparative analysis of both attacks and defenses. The authors also present an open‑source toolbox on GitHub to support further research in this area.
arXiv:2411. 10023v3 Announce Type: replace Abstract: Deep neural networks have enabled numerous studies and applications on both Euclidean data, such as images and text, and non-Euclidean data, such as graphs.
arXiv:2610.07677v1 Announce Type: new Abstract: In this paper, we show that standard evaluations of high-resolution Model Inversion Attacks (MIAs) significantly underestimate training-data privacy le...
In this paper, we show that standard evaluations of high-resolution Model Inversion Attacks (MIAs) significantly underestimate training-data privacy leakage. State-of-the-art privacy defenses, standar...
arXiv:2409. 01062v4 Announce Type: replace Abstract: Model Inversion (MI) attacks pose a significant privacy threat by reconstructing private training data from machine learning models.
arXiv:2505. 19840v3 Announce Type: replace-cross Abstract: Deep Neural Networks (DNNs) have achieved widespread success yet remain prone to adversarial attacks.
The paper investigates provable privacy attacks on trained 2‑layer ReLU neural networks, specifically membership inference and data reconstruction. It demonstrates that the implicit bias of such networks can be leveraged to identify, with high probability, whether a given point was part of the training set in high‑dimensional, nearly orthogonal settings, and to construct a finite set containing a constant fraction of training points in a univariate setting. This work claims to be the first to reveal provable vulnerabilities arising from implicit bias in shallow neural networks.
arXiv:2606. 29748v1 Announce Type: new Abstract: The application of graph data in numerous disciplines raises the need for gathering and analyzing huge volumes of data, some of which is private and sensitive.
arXiv:2606. 14210v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in privacy-sensitive domains, where users must balance the risk of data exposure through external APIs against the high computational cost of local deployment.
arXiv:2610.27152v1 Announce Type: cross Abstract: Neural networks (NNs) are increasingly deployed on edge devices such as mobile and IoT platforms, offering low latency and improved privacy compared...
arXiv:2507. 01752v4 Announce Type: replace-cross Abstract: Gradient-based optimization is the workhorse of deep learning, offering efficient and scalable training via backpropagation.
The paper "Timing is Everything: Inferring Temporal Membership in Continually Updated Models" presents the first systematic study of temporal privacy risk in continually updated deep learning models. It formalizes temporal membership and introduces the temporal membership inference attack (TMIA), a black-box method that uses bidirectional LSTMs to infer when individual samples were used in training at both timestamp- and interval-level granularity. Experiments on language and image models demonstrate TMIA’s effectiveness, and the authors evaluate three defenses, highlighting a trade-off between privacy protection and model utility.
arXiv:2607. 12354v1 Announce Type: new Abstract: In this paper, we challenge the prevailing view that information dependency (including rote memorization) drives training data exposure to image reconstruction attacks.