English
Related papers

Related papers: Combing for Credentials: Active Pattern Extraction…

200 papers

The privacy of machine learning models has become a significant concern in many emerging Machine-Learning-as-a-Service applications, where prediction services based on well-trained models are offered to users via pay-per-query. The lack of…

Machine Learning · Computer Science 2022-06-24 Xun Xian , Mingyi Hong , Jie Ding

Neural networks are often trained on proprietary datasets, making them attractive attack targets. We present a novel dataset extraction method leveraging an innovative training time backdoor attack, allowing a malicious federated learning…

Cryptography and Security · Computer Science 2025-12-19 Eden Luzon , Guy Amit , Roy Weiss , Torsten Kraub , Alexandra Dmitrienko , Yisroel Mirsky

The advance of explainable artificial intelligence, which provides reasons for its predictions, is expected to accelerate the use of deep neural networks in the real world like Machine Learning as a Service (MLaaS) that returns predictions…

Cryptography and Security · Computer Science 2021-07-20 Takayuki Miura , Satoshi Hasegawa , Toshiki Shibahara

Adversarial extraction attacks constitute an insidious threat against Deep Learning (DL) models in-which an adversary aims to steal the architecture, parameters, and hyper-parameters of a targeted DL model. Existing extraction attack…

Cryptography and Security · Computer Science 2023-02-01 William Hackett , Stefan Trawicki , Zhengxin Yu , Neeraj Suri , Peter Garraghan

Previous work has shown that Large Language Models are susceptible to so-called data extraction attacks. This allows an attacker to extract a sample that was contained in the training data, which has massive privacy implications. The…

Computation and Language · Computer Science 2023-02-16 Ali Al-Kaswan , Maliheh Izadi , Arie van Deursen

Machine learning (ML) applications are increasingly prevalent. Protecting the confidentiality of ML models becomes paramount for two reasons: (a) a model can be a business advantage to its owner, and (b) an adversary may use a stolen model…

Cryptography and Security · Computer Science 2019-04-02 Mika Juuti , Sebastian Szyller , Samuel Marchal , N. Asokan

Large language models (LLMs) are inherently vulnerable to unintended privacy breaches. Consequently, systematic red-teaming research is essential for developing robust defense mechanisms. However, current data extraction methods suffer from…

Machine Learning · Computer Science 2025-05-13 Zhiqiang Wang , Ruoxi Cheng

Fine-tuning has emerged as a critical process in leveraging Large Language Models (LLMs) for specific downstream tasks, enabling these models to achieve state-of-the-art performance across various domains. However, the fine-tuning process…

Artificial Intelligence · Computer Science 2025-04-08 Hao Du , Shang Liu , Lele Zheng , Yang Cao , Atsuyoshi Nakamura , Lei Chen

Large pre-trained models have achieved notable success across a range of downstream tasks. However, recent research shows that a type of adversarial attack ($\textit{i.e.,}$ backdoor attack) can manipulate the behavior of machine learning…

Artificial Intelligence · Computer Science 2024-10-29 Dongliang Guo , Mengxuan Hu , Zihan Guan , Junfeng Guo , Thomas Hartvigsen , Sheng Li

Pre-trained general-purpose language models have been a dominating component in enabling real-world natural language processing (NLP) applications. However, a pre-trained model with backdoor can be a severe threat to the applications. Most…

Computation and Language · Computer Science 2021-11-02 Lujia Shen , Shouling Ji , Xuhong Zhang , Jinfeng Li , Jing Chen , Jie Shi , Chengfang Fang , Jianwei Yin , Ting Wang

In a model extraction attack, an adversary steals a copy of a remotely deployed machine learning model, given oracle prediction access. We taxonomize model extraction attacks around two objectives: *accuracy*, i.e., performing well on the…

Machine Learning · Computer Science 2020-03-05 Matthew Jagielski , Nicholas Carlini , David Berthelot , Alex Kurakin , Nicolas Papernot

Language model attacks typically assume one of two extreme threat models: full white-box access to model weights, or black-box access limited to a text generation API. However, real-world APIs are often more flexible than just text…

Cryptography and Security · Computer Science 2024-08-06 Kellin Pelrine , Mohammad Taufeeque , Michał Zając , Euan McLean , Adam Gleave

Models leak information about their training data. This enables attackers to infer sensitive information about their training sets, notably determine if a data sample was part of the model's training set. The existing works empirically show…

Machine Learning · Statistics 2021-02-18 Sasi Kumar Murakonda , Reza Shokri , George Theodorakopoulos

Machine learning (ML) models may be deemed confidential due to their sensitive training data, commercial value, or use in security applications. Increasingly often, confidential ML models are being deployed with publicly accessible query…

Cryptography and Security · Computer Science 2016-10-04 Florian Tramèr , Fan Zhang , Ari Juels , Michael K. Reiter , Thomas Ristenpart

Ensuring the security of large language models (LLMs) is an ongoing challenge despite their widespread popularity. Developers work to enhance LLMs security, but vulnerabilities persist, even in advanced versions like GPT-4. Attackers…

Cryptography and Security · Computer Science 2023-12-19 Aysan Esmradi , Daniel Wankit Yip , Chun Fai Chan

Machine Learning models, extensively used for various multimedia applications, are offered to users as a blackbox service on the Cloud on a pay-per-query basis. Such blackbox models are commercially valuable to adversaries, making them…

Cryptography and Security · Computer Science 2020-02-04 Vasisht Duddu , D. Vijay Rao

Large language models have gained significant popularity because of their ability to generate human-like text and potential applications in various fields, such as Software Engineering. Large language models for code are commonly trained on…

Cryptography and Security · Computer Science 2024-01-17 Ali Al-Kaswan , Maliheh Izadi , Arie van Deursen

This paper studies extractable memorization: training data that an adversary can efficiently extract by querying a machine learning model without prior knowledge of the training dataset. We show an adversary can extract gigabytes of…

We introduce a new class of attacks on machine learning models. We show that an adversary who can poison a training dataset can cause models trained on this dataset to leak significant private details of training points belonging to other…

Cryptography and Security · Computer Science 2022-10-07 Florian Tramèr , Reza Shokri , Ayrton San Joaquin , Hoang Le , Matthew Jagielski , Sanghyun Hong , Nicholas Carlini

The pre-training and fine-tuning paradigm has demonstrated its effectiveness and has become the standard approach for tailoring language models to various tasks. Currently, community-based platforms offer easy access to various pre-trained…

Cryptography and Security · Computer Science 2024-09-17 Ruixuan Liu , Tianhao Wang , Yang Cao , Li Xiong