Forget What's Sensitive, Remember What Matters: Token-Level Differential Privacy in Memory Sculpting for Continual Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhan, Bihao, Zhou, Jie, Li, Junsong, Yang, Yutao, Chen, Shilian, Pan, Qianjun, Li, Xin, Wu, Wen, Wu, Xingjiao, Chen, Qin, Yan, Hang, He, Liang
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917521261592576
author Zhan, Bihao
Zhou, Jie
Li, Junsong
Yang, Yutao
Chen, Shilian
Pan, Qianjun
Li, Xin
Wu, Wen
Wu, Xingjiao
Chen, Qin
Yan, Hang
He, Liang
author_facet Zhan, Bihao
Zhou, Jie
Li, Junsong
Yang, Yutao
Chen, Shilian
Pan, Qianjun
Li, Xin
Wu, Wen
Wu, Xingjiao
Chen, Qin
Yan, Hang
He, Liang
contents Continual Learning (CL) models, while adept at sequential knowledge acquisition, face significant and often overlooked privacy challenges due to accumulating diverse information. Traditional privacy methods, like a uniform Differential Privacy (DP) budget, indiscriminately protect all data, leading to substantial model utility degradation and hindering CL deployment in privacy-sensitive areas. To overcome this, we propose a privacy-enhanced continual learning (PeCL) framework that forgets what's sensitive and remembers what matters. Our approach first introduces a token-level dynamic Differential Privacy strategy that adaptively allocates privacy budgets based on the semantic sensitivity of individual tokens. This ensures robust protection for private entities while minimizing noise injection for non-sensitive, general knowledge. Second, we integrate a privacy-guided memory sculpting module. This module leverages the sensitivity analysis from our dynamic DP mechanism to intelligently forget sensitive information from the model's memory and parameters, while explicitly preserving the task-invariant historical knowledge crucial for mitigating catastrophic forgetting. Extensive experiments show that PeCL achieves a superior balance between privacy preserving and model utility, outperforming baseline models by maintaining high accuracy on previous tasks while ensuring robust privacy.
format Preprint
id arxiv_https___arxiv_org_abs_2509_12958
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Forget What's Sensitive, Remember What Matters: Token-Level Differential Privacy in Memory Sculpting for Continual Learning
Zhan, Bihao
Zhou, Jie
Li, Junsong
Yang, Yutao
Chen, Shilian
Pan, Qianjun
Li, Xin
Wu, Wen
Wu, Xingjiao
Chen, Qin
Yan, Hang
He, Liang
Artificial Intelligence
Continual Learning (CL) models, while adept at sequential knowledge acquisition, face significant and often overlooked privacy challenges due to accumulating diverse information. Traditional privacy methods, like a uniform Differential Privacy (DP) budget, indiscriminately protect all data, leading to substantial model utility degradation and hindering CL deployment in privacy-sensitive areas. To overcome this, we propose a privacy-enhanced continual learning (PeCL) framework that forgets what's sensitive and remembers what matters. Our approach first introduces a token-level dynamic Differential Privacy strategy that adaptively allocates privacy budgets based on the semantic sensitivity of individual tokens. This ensures robust protection for private entities while minimizing noise injection for non-sensitive, general knowledge. Second, we integrate a privacy-guided memory sculpting module. This module leverages the sensitivity analysis from our dynamic DP mechanism to intelligently forget sensitive information from the model's memory and parameters, while explicitly preserving the task-invariant historical knowledge crucial for mitigating catastrophic forgetting. Extensive experiments show that PeCL achieves a superior balance between privacy preserving and model utility, outperforming baseline models by maintaining high accuracy on previous tasks while ensuring robust privacy.
title Forget What's Sensitive, Remember What Matters: Token-Level Differential Privacy in Memory Sculpting for Continual Learning
topic Artificial Intelligence
url https://arxiv.org/abs/2509.12958