English
Related papers

Related papers: Mitigating Gradient Inversion Risks in Language Mo…

200 papers

Collaborative machine learning settings like federated learning can be susceptible to adversarial interference and attacks. One class of such attacks is termed model inversion attacks, characterised by the adversary reverse-engineering the…

Machine Learning · Computer Science 2022-03-02 Dmitrii Usynin , Daniel Rueckert , Georgios Kaissis

Embeddings have become a cornerstone in the functionality of large language models (LLMs) due to their ability to transform text data into rich, dense numerical representations that capture semantic and syntactic properties. These embedding…

Cryptography and Security · Computer Science 2025-11-20 Tiantian Liu , Hongwei Yao , Feng Lin , Tong Wu , Zhan Qin , Kui Ren

Graph Neural Networks (GNNs) have emerged as powerful models for learning from graph-structured data. However, their widespread adoption has raised serious privacy concerns. While prior research has primarily focused on edge-level privacy,…

Machine Learning · Computer Science 2025-11-12 Jie Fu , Yuan Hong , Zhili Chen , Wendy Hui Wang

Obfuscation stands as a promising solution for safeguarding hardware intellectual property (IP) against a spectrum of threats including reverse engineering, IP piracy, and tampering. In this paper, we introduce Obfus-chat, a novel framework…

In this work, we consider an inversion attack on the obfuscated input embeddings sent to a language model on a server, where the adversary has no access to the language model or the obfuscation mechanism and sees only the obfuscated…

Cryptography and Security · Computer Science 2025-05-21 Kaan Kale , Kyle Mylonakis , Jay Roberts , Sidhartha Roy

Box-free model watermarking has gained significant attention in deep neural network (DNN) intellectual property protection due to its model-agnostic nature and its ability to flexibly manage high-entropy image outputs from generative…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Haonan An , Guang Hua , Wei Du , Hangcheng Cao , Yihang Tao , Guowen Xu , Susanto Rahardja , Yuguang Fang

Federated Learning (FL) framework brings privacy benefits to distributed learning systems by allowing multiple clients to participate in a learning task under the coordination of a central server without exchanging their private data.…

Computer Vision and Pattern Recognition · Computer Science 2022-03-30 Zhuohang Li , Jiaxin Zhang , Luyang Liu , Jian Liu

The privacy vulnerabilities of the federated learning (FL) paradigm, primarily caused by gradient leakage, have prompted the development of various defensive measures. Nonetheless, these solutions have predominantly been crafted for and…

Cryptography and Security · Computer Science 2025-02-10 Abhinav Kumar , George Torres , Noah Guzinski , Gaurav Panwar , Reza Tourani , Satyajayant Misra , Marcin Spoczynski , Mona Vij , Nageen Himayat

Although federated learning has increasingly gained attention in terms of effectively utilizing local devices for data privacy enhancement, recent studies show that publicly shared gradients in the training process can reveal the private…

Cryptography and Security · Computer Science 2021-09-22 Jieren Deng , Yijue Wang , Ji Li , Chao Shang , Hang Liu , Sanguthevar Rajasekaran , Caiwen Ding

Gradient inversion attacks reveal that private training text can be reconstructed from shared gradients, posing a privacy risk to large language models (LLMs). While prior methods perform well in small-batch settings, scaling to larger…

Machine Learning · Computer Science 2026-03-18 Yibo Li , Qiongxiu Li

Federated Learning (FL) aims to protect data privacy by enabling clients to collectively train machine learning models without sharing their raw data. However, recent studies demonstrate that information exchanged during FL is subject to…

Machine Learning · Computer Science 2024-12-11 Pengxin Guo , Shuang Zeng , Wenhao Chen , Xiaodan Zhang , Weihong Ren , Yuyin Zhou , Liangqiong Qu

Gradient-based adversarial training is widely used in improving the robustness of neural networks, while it cannot be easily adapted to natural language processing tasks since the embedding space is discrete. In natural language processing…

Computation and Language · Computer Science 2020-12-07 Linyang Li , Xipeng Qiu

This paper presents a holistic approach to gradient leakage resilient distributed Stochastic Gradient Descent (SGD). First, we analyze two types of strategies for privacy-enhanced federated learning: (i) gradient pruning with random…

Machine Learning · Computer Science 2023-05-12 Wenqi Wei , Ling Liu , Jingya Zhou , Ka-Ho Chow , Yanzhao Wu

In Federated Learning (FL), clients share gradients with a central server while keeping their data local. However, malicious servers could deliberately manipulate the models to reconstruct clients' data from shared gradients, posing…

Cryptography and Security · Computer Science 2025-04-11 Kunlan Xiang , Haomiao Yang , Meng Hao , Shaofeng Li , Haoxin Wang , Zikang Ding , Wenbo Jiang , Tianwei Zhang

Federated learning claims to enable collaborative model training among multiple clients with data privacy by transmitting gradient updates instead of the actual client data. However, recent studies have shown the client privacy is still at…

Machine Learning · Computer Science 2025-03-04 Maria Drencheva , Ivo Petrov , Maximilian Baader , Dimitar I. Dimitrov , Martin Vechev

Machine-generated Text (MGT) detection is crucial for regulating and attributing online texts. While the existing MGT detectors achieve strong performance, they remain vulnerable to simple perturbations and adversarial attacks. To build an…

Cryptography and Security · Computer Science 2025-05-01 Yuanfan Li , Zhaohan Zhang , Chengzhengxu Li , Chao Shen , Xiaoming Liu

Federated Learning is a machine learning setting that reduces direct data exposure, improving the privacy guarantees of machine learning models. Yet, the exchange of model updates between the participants and the aggregator can still leak…

Machine Learning · Computer Science 2025-12-18 Pablo Montaña-Fernández , Ines Ortega-Fernandez

We present GIFT: a {G}radient-aware {I}mmunization technique to defend diffusion models against malicious {F}ine-{T}uning while preserving their ability to generate safe content. Existing safety mechanisms like safety checkers are easily…

Cryptography and Security · Computer Science 2025-07-21 Amro Abdalla , Ismail Shaheen , Dan DeGenaro , Rupayan Mallick , Bogdan Raita , Sarah Adel Bargal

Conventional adversarial defenses reduce classification accuracy whether or not a model is under attacks. Moreover, most of image processing based defenses are defeated due to the problem of obfuscated gradients. In this paper, we propose a…

Machine Learning · Computer Science 2020-05-19 MaungMaung AprilPyone , Hitoshi Kiya

Federated Learning (FL) is a distributed learning paradigm that enhances users privacy by eliminating the need for clients to share raw, private data with the server. Despite the success, recent studies expose the vulnerability of FL to…

Machine Learning · Computer Science 2023-12-15 Jing Wu , Munawar Hayat , Mingyi Zhou , Mehrtash Harandi