No article text was recorded for this version.
transformer privacy vulnerability
Version 1 of 131 papers48 conceptsfrozen 2026-10-04
Papers in this version
- Blog: How Does a Deep Learning Model Architecture Impact Its Privacy? A Comprehensive Study of Privacy Attacks on CNNs and Transformers
- Blog: Unmasking Transformers: A Theoretical Approach to Data Recovery via Attention Weights
- Blog: GradViT: Gradient Inversion of Vision Transformers
- Blog: Differentially Private Attention Computation
- Blog: Privacy-Preserving Split Learning with Vision Transformers using Patch-Wise Random and Noisy CutMix
- Blog: APRIL: Finding the Achilles' Heel on Privacy for Vision Transformers
- Blog: Black-Box Dissector: Towards Erasing-Based Hard-Label Model Stealing Attack
- Blog: ADePT: Auto-encoder based Differentially Private Text Transformation
- Blog: Private Language Models via Truncated Laplacian Mechanism
- Blog: Enhancing Privacy in Multimodal Federated Learning with Information Theory
- Blog: Information Removal at the bottleneck in Deep Neural Networks
- Blog: Towards Understanding and Improving Adversarial Robustness of Vision Transformers
- Blog: TS-Inverse: A Gradient Inversion Attack Tailored for Federated Time Series Forecasting Models
- Blog: Leave-one-out Distinguishability in Machine Learning
- Blog: Generative AI model privacy: a survey
- Blog: A Survey on Gradient Inversion: Attacks, Defenses and Future Directions
- Blog: Vicious Classifiers: Assessing Inference-time Data Reconstruction Risk in Edge Computing
- Blog: Disrupting Diffusion: Token-Level Attention Erasure Attack against Diffusion-based Customization
- Blog: Privacy Regularization: Joint Privacy-Utility Optimization in LanguageModels
- Blog: Memorization in NLP Fine-tuning Methods
- Blog: Seeing the Forest through the Trees: Data Leakage from Partial Transformer Gradients
- Blog: Balancing Privacy and Action Performance: A Penalty-Driven Approach to Image Anonymization
- Blog: Do Gradient Inversion Attacks Make Federated Learning Unsafe?
- Blog: Analysis of Privacy Leakage in Federated Large Language Models
- Blog: Preserving differential privacy in convolutional deep belief networks
- Blog: Theoretically Unmasking Inference Attacks Against LDP-Protected Clients in Federated Vision Models
- Blog: Selective Differential Privacy for Language Modeling
- Blog: DRAG: Data Reconstruction Attack using Guided Diffusion
- Blog: Towards Privacy-Preserving Split Learning: Destabilizing Adversarial Inference and Reconstruction Attacks in the Cloud
- Blog: DAGER: Exact Gradient Inversion for Large Language Models
- Blog: Membership Inference Attacks Against In-Context Learning
History & citation
Current · Permanent link
- This direction split from Data Leakage through Transformer Attention Mechanisms (52% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_transformer_privacy_vulnerability_2624d4de,
title = {transformer privacy vulnerability},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/transformer-privacy-vulnerability/rdr_2624d4de69fb42069050cd6bfb749f39},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_transformer_privacy_vulnerability_2624d4de_v1,
title = {transformer privacy vulnerability},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/transformer-privacy-vulnerability/rdr_2624d4de69fb42069050cd6bfb749f39/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}