Reconstruction Attack on Instance Encoding for Language Understanding (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing private learning schemes which protect data privacy can be used to train models using instance encoding. |
| Approach: | They propose to recover the private training data and use it to break a private learning scheme TextHide. |
| Outcome: | The proposed attack would advance privacy-preserving machine learning in the context of natural language processing. |
Similar Papers
Differentially Private Instance Encoding against Privacy Attacks (2022.naacl-srw)
Copied to clipboard
| Challenge: | TextHide is a proposed privacy-enhancing technology to protect the training data from privacy attacks. |
| Approach: | They propose to encode training data via instance encoding in natural language domain without theoretic privacy guarantee. |
| Outcome: | The proposed scheme can defend against privacy attacks while ensuring learning utility (as a trade-off). |
TextHide: Tackling Data Privacy in Language Understanding Tasks (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Unsolved privacy challenges in distributed or federated learning are a challenge for many domains including Natural Language Processing. |
| Approach: | They propose a federated learning framework that adds an encryption step to prevent an eavesdropping attacker from recovering private text data. |
| Outcome: | The proposed model can effectively defend against attacks on shared gradients or representations and the averaged accuracy reduction is only 1.9%. |
Privacy-preserving Neural Representations of Text (D18-1)
Copied to clipboard
| Challenge: | a specific type of attack is used to characterize the privacy of neural representations for NLP tasks, in the context of privacy protection. |
| Approach: | They propose several defense methods based on modified training objectives and characterize the tradeoff between privacy and the utility of neural representations. |
| Outcome: | The proposed defenses improve the privacy of neural representations and characterize the tradeoff between privacy and utility of representations. |
Revisiting Data Reconstruction Attacks on Real-world Dataset for Federated Natural Language Understanding (2024.lrec-main)
Copied to clipboard
Zhuo Zhang, Jintao Huang, Xiangjing Hu, Jingyuan Zhang, Yating Zhang, Hui Wang, Yue Yu, Qifan Wang, Lizhen Qu, Zenglin Xu
| Challenge: | Existing DRA methods fail to accurately recover the original text of real-world privacy data. |
| Approach: | They propose to use a real-world privacy dataset to examine the performance of federated learning (FL) methods. |
| Outcome: | The proposed method improves on a real-world privacy dataset and shows that the tokens within a recovery sentence are disordered and intertwined with tokens from other sentences in the same training batch. |
Federated Model Decomposition with Private Vocabulary for Text Classification (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to train federated learning (FL) for natural language processing require sensitive data to leave local devices. |
| Approach: | They propose a fedrated model decomposition method that protects the privacy of vocabularies . they propose an adaptive updating technique to improve the performance of local models . |
| Outcome: | The proposed method protects the privacy of vocabularies in federated learning tasks . it maintains competitive performance and provides better privacy-preserving capacity compared to status quo methods. |
On the Vulnerability of Text Sanitization (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing reconstruction attacks on text sanitization are not able to accurately assess their effectiveness. |
| Approach: | They propose to use ASR to measure the effectiveness of reconstruction attacks to evaluate sanitization performance. |
| Outcome: | The proposed reconstruction attacks achieve a 46.4% improvement in ASR over the state-of-the-art baseline with a privacy budget of =4.0 on the SST-2 dataset. |
CAPE: Context-Aware Private Embeddings for Private Language Learning (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to obtain text representations or embeddings with these models encoding personally identifiable information may lead to privacy leaks. |
| Approach: | They propose a novel approach which combines differential privacy and adversarial learning to preserve privacy during training of embeddings. |
| Outcome: | The proposed approach reduces private information leakage by 3% over the current method. |
Privacy-Preserving Natural Language Processing (2023.eacl-tutorials)
Copied to clipboard
| Challenge: | This tutorial will help the NLP community to get familiar with current research in privacy-preserving methods. |
| Approach: | This tutorial will help the NLP community to get familiar with current research in privacy-preserving methods. |
| Outcome: | The tutorial will cover membership inference, differential privacy, homomorphic encryption, or federated learning, all with typical use-cases and potential pitfalls. |
TextObfuscator: Making Pre-trained Language Model a Privacy Protector via Obfuscating Word Representations (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing inference services are plagued by privacy concerns, such as sharing sensitive data with service providers. |
| Approach: | They propose a framework for protecting inference privacy by applying random perturbations to clustered representations. |
| Outcome: | The proposed framework protects inference privacy by applying random perturbations to clustered representations. |
Stealing Training Data from Large Language Models in Decentralized Training through Activation Inversion Attack (2025.acl-long)
Copied to clipboard
| Challenge: | Decentralized training is a resource-efficient framework to democratize training of large language models. |
| Approach: | They propose an activation inversion attack to exploit privacy leakage from training data . they construct a shadow dataset comprising text labels and corresponding activations . |
| Outcome: | The proposed attack surface is based on a shadow dataset and public datasets . the proposed attack model reconstructs training data from activations in victim decentralized training. |