# Leveraging Soft Prompts for Privacy Attacks in Federated Prompt Tuning

DevFeed: [Leveraging Soft Prompts for Privacy Attacks in Federated Prompt Tuning](<https://devfeed.tech/articles/leveraging-soft-prompts-for-privacy-attacks-in-federated-prompt-tuning-118661.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2601.06641>)

Author: Quan Minh Nguyen, Min-Seon Kim, Hoang M. Ngo, Trong Nghia Hoang, Hyuk-Yoon Kwon, My T. Thai

Published: 2026-11-05T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [Adversarial attacks](<https://devfeed.tech/topics/adversarial-attacks.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [also](<https://devfeed.tech/tags/also.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [attack](<https://devfeed.tech/tags/attack.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [client](<https://devfeed.tech/tags/client.md>), [client-s](<https://devfeed.tech/tags/client-s.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [defense](<https://devfeed.tech/tags/defense.md>), [effective](<https://devfeed.tech/tags/effective.md>), [existing](<https://devfeed.tech/tags/existing.md>), [exploits](<https://devfeed.tech/tags/exploits.md>), [federated](<https://devfeed.tech/tags/federated.md>), [leveraging](<https://devfeed.tech/tags/leveraging.md>), [privacy](<https://devfeed.tech/tags/privacy.md>), [prompt](<https://devfeed.tech/tags/prompt.md>)

## AI overview

PromptMIA exploits federated prompt-tuning as a membership-inference attack surface: a malicious server injects adversarially crafted prompts and uses their training updates to infer whether a target example appears in a client's private dataset. The authors formalize the threat with a security game and report consistently high attack advantage across diverse benchmarks, substantially outperforming existing federated MIAs. They also derive a lower bound intended to explain the observed results. Existing MIA defenses are often ineffective against this attack, motivating defenses tailored to prompt-tuning in federated settings. These claims are based on the supplied abstract.

## Source excerpt

arXiv:2601.06641v4 Announce Type: replace-cross Abstract: Membership inference attacks (MIAs) pose a serious privacy threat in federated learning (FL). While MIAs have been extensively studied in standard FL, the recent shift toward federated fine-tuning introduces new and largely unexplored attack surfaces. In this work, we show that federated prompt-tuning, which adapts pre-trained foundation models using lightweight input prefixes, exposes a novel and effective vector for membership inference. We propose PromptMIA, a membership inference attack tailored to federated prompt-tuning, in which a malicious server introduces adversarially crafted prompts and exploits their updates during collaborative training to determine whether a target data point belongs to a client's private dataset. We formalize this threat via a security game and demonstrate that PromptMIA achieves consistently high attack advantage across diverse benchmark datasets, substantially outperforming current SOTA federated MIAs. We also provide a theoretical lower bound on the attack advantage that explains the observed empirical behavior. Finally, we show that existing MIA defenses are often ineffective against PromptMIA, highlighting the need for defense mechanisms specifically tailored to prompt-tuning in federated settings.