Challenge: Existing studies have demonstrated that pretrained language models memorize and regurgitate a significant portion of training data, including atypical data points that appear only once in the training data.
Approach: They propose a method to locate and erase risky neurons in order to eliminate the impact of privacy data in the model in batches.
Outcome: The proposed method eliminates the impact of privacy data in the model in batches without affecting the model's performance.

Similar Papers

Knowledge Unlearning for Mitigating Privacy Risks in Language Models (2023.acl-long)

Copied to clipboard

Challenge: Recent work shows that an adversary can extract training data from Pretrained Language Models including Personally Identifiable Information (PII) such as names, phone numbers, and email addresses.
Approach: They propose to use knowledge unlearning to reduce privacy risks for LMs by performing gradient ascent on target token sequences instead of trying to unlearn all the data at once.
Outcome: The proposed method can give a stronger empirical privacy guarantee in scenarios where the data vulnerable to extraction attacks are known a priori while being much more efficient and robust.
Preserving Privacy Through Dememorization: An Unlearning Technique For Mitigating Memorization Risks In Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: Large Language models (LLMs) are trained on vast amounts of data, including sensitive information that poses a risk to personal privacy if exposed.
Approach: They propose a novel unlearning approach that utilizes an efficient reinforcement learning feedback loop via proximal policy optimization to incentivize the LLMs to learn a paraphrasing policy to unlearn the pre-training data.
Outcome: The proposed approach surpasses strong baselines and state-of-the-art methods in terms of its ability to generalize and strike a balance between privacy and LLM performance.
Learnable Privacy Neurons Localization in Language Models (2024.acl-short)

Copied to clipboard

Challenge: Large Language Models (LLMs) memorize and disclose private information, especially Personally Identifiable Information (PII) concerns regarding privacy and security within human society remain poorly understood.
Approach: They propose to use learnable binary weight masks to localize PII-sensitive neurons within LLMs by deactivating localized privacy neurons.
Outcome: The proposed method localizes PII-sensitive neurons across all layers and shows the property of PI I specificity.
REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space (2025.findings-acl)

Copied to clipboard

Challenge: Current approaches to address this issue involve costly dataset scrubbing or model filtering through unlearning and model editing.
Approach: They propose a method for unlearning sensitive information from language models . they curate email and URL datasets and a social security number dataset .
Outcome: The proposed method shows superior performance and robustness to extraction attacks on real-world datasets.
Protecting Privacy Through Approximating Optimal Parameters for Sequence Unlearning in Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Language models (LMs) demonstrate exceptional capabilities on tasks, but are vulnerable to extraction attacks.
Approach: They propose Privacy Protection via Optimal Parameters (POP) which induces the model to forget about some of its training data.
Outcome: The proposed method outperforms the state-of-the-art in retaining LM performance on 9 classification and 4 dialogue benchmarks.
Adapting Language Models When Training on Privacy-Transformed Data (2022.lrec-1)

Copied to clipboard

Challenge: Using data sanitization methods to remove personal information from spoken messages is not effective because privacy-transformed data is unlikely to match the test distribution.
Approach: They propose to use a data sanitization approach to remove personal information from spoken messages by replacing named entities with other words from the same class.
Outcome: The proposed approach removes personal information from the spoken messages using an automatic named entity recognition method.
Training Text-to-Text Transformers with Privacy Guarantees (2022.findings-acl)

Copied to clipboard

Challenge: Recent advances in NLP often stem from large transformer-based pre-trained models.
Approach: They propose differentially private (DP) training as a potential mitigation for models that can memorize parts of training data.
Outcome: The proposed model can memorize parts of training data and mitigate memorization concerns.
Neural Text Sanitization with Explicit Measures of Privacy Risk (2022.aacl-main)

Copied to clipboard

Challenge: Personal data, also known as Personally Identifiable Information (PII), often abound in text documents.
Approach: They propose a method for text sanitization that uses a neural entity recognizer to detect and classify potential personal identifiers and a classifier trained on labelled data to determine which entities to mask .
Outcome: The proposed approach masks all personal identifiers and thereby conceals the identity of the individuals mentioned in the document.
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.
Private Memorization Editing: Turning Memorization into a Defense to Strengthen Data Privacy in Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) memorize and therefore, among huge amounts of uncontrolled data, may memorize Personally Identifiable Information (PII).
Approach: They propose a method that uses a model knowledge to memorize PII from training data to mitigate the memorization of PI I.
Outcome: The proposed method reduces the number of leaked PIIs in a number of configurations while making it more robust against privacy Training Data Extraction attacks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations