English
Related papers

Related papers: Extracting Training Data from Large Language Model…

200 papers

Sophisticated language models such as OpenAI's GPT-3 can generate hateful text that targets marginalized groups. Given this capacity, we are interested in whether large language models can be used to identify hate speech and classify text…

Computation and Language · Computer Science 2022-03-25 Ke-Li Chiu , Annie Collins , Rohan Alexander

Large language models (LLMs) are susceptible to memorizing training data, raising concerns about the potential extraction of sensitive information at generation time. Discoverable extraction is the most common method for measuring this…

Differentially private training algorithms like DP-SGD protect sensitive training data by ensuring that trained models do not reveal private information. An alternative approach, which this paper studies, is to use a sensitive dataset to…

Machine Learning · Computer Science 2024-01-12 Alexey Kurakin , Natalia Ponomareva , Umar Syed , Liam MacDermed , Andreas Terzis

Language models are widely deployed to provide automatic text completion services in user products. However, recent research has revealed that language models (especially large ones) bear considerable risk of memorizing private training…

Computation and Language · Computer Science 2022-12-19 C. M. Downey , Wei Dai , Huseyin A. Inan , Kim Laine , Saurabh Naik , Tomasz Religa

Model extraction emerges as a critical security threat with attack vectors exploiting both algorithmic and implementation-based approaches. The main goal of an attacker is to steal as much information as possible about a protected victim…

Cryptography and Security · Computer Science 2024-11-18 Kevin Hector , Pierre-Alain Moellic , Mathieu Dumont , Jean-Max Dutertre

Amidst the rapid advancements in generative language models, the investigation of how training data shapes the performance of GPT models is still emerging. This paper presents GPTfluence, a novel approach that leverages a featurized…

Computation and Language · Computer Science 2024-10-04 Yekun Chai , Qingyi Liu , Shuohuan Wang , Yu Sun , Qiwei Peng , Hua Wu

Large Language Models (LLMs) are increasingly deployed in sensitive domains including healthcare, legal services, and confidential communications, where privacy is paramount. This paper introduces Whisper Leak, a side-channel attack that…

Cryptography and Security · Computer Science 2025-11-06 Geoff McDonald , Jonathan Bar Or

Pretrained language models are typically trained on massive web-based datasets, which are often "contaminated" with downstream test sets. It is not clear to what extent models exploit the contaminated data for downstream tasks. We present a…

Computation and Language · Computer Science 2022-03-17 Inbal Magar , Roy Schwartz

This paper identifies and analyzes applications in which Large Language Models (LLMs) can make Internet of Things (IoT) networks more intelligent and responsive through three case studies from critical topics: DDoS attack detection,…

Artificial Intelligence · Computer Science 2024-10-28 Mingyu Zong , Arvin Hekmati , Michael Guastalla , Yiyi Li , Bhaskar Krishnamachari

Many recent efforts augment language models with retrieval, by adding retrieved data to the input context. For this approach to succeed, the retrieved data must be added at both training and test time. Moreover, as input length grows…

Computation and Language · Computer Science 2024-02-06 Moritz Hardt , Yu Sun

With a handful of demonstration examples, large-scale language models show strong capability to perform various tasks by in-context learning from these examples, without any fine-tuning. We demonstrate that in-context learning performance…

Computation and Language · Computer Science 2022-11-10 Yiming Zhang , Shi Feng , Chenhao Tan

The raise of machine learning and deep learning led to significant improvement in several domains. This change is supported by both the dramatic rise in computation power and the collection of large datasets. Such massive datasets often…

Machine Learning · Computer Science 2022-11-24 Hamid Jalalzai , Elie Kadoche , Rémi Leluc , Vincent Plassier

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

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

Modern language models (LM) are trained on large scrapes of the Web, containing millions of personal information (PI) instances, many of which LMs memorize, increasing privacy risks. In this work, we develop the regexes and rules (R&R)…

Computation and Language · Computer Science 2026-02-25 Nishant Subramani , Kshitish Ghate , Mona Diab

Language modeling is a keystone task in natural language processing. When training a language model on sensitive information, differential privacy (DP) allows us to quantify the degree to which our private data is protected. However,…

Machine Learning · Computer Science 2020-10-27 Gavin Kerrigan , Dylan Slack , Jens Tuyls

As Large Language Models (LLMs) become increasingly widespread, understanding how specific training data shapes their outputs is crucial for transparency, accountability, privacy, and fairness. To explore how LLMs leverage and replicate…

Computation and Language · Computer Science 2025-07-03 Arthur Wuhrmann , Anastasiia Kucherenko , Andrei Kucharavy

Previous learning-based vulnerability detection methods relied on either medium-sized pre-trained models or smaller neural networks from scratch. Recent advancements in Large Pre-Trained Language Models (LLMs) have showcased remarkable…

Software Engineering · Computer Science 2024-01-30 Xin Zhou , Ting Zhang , David Lo

Recent studies have demonstrated the vulnerability of recommender systems to data privacy attacks. However, research on the threat to model privacy in recommender systems, such as model stealing attacks, is still in its infancy. Some…

Cryptography and Security · Computer Science 2023-12-27 Zhihao Zhu , Rui Fan , Chenwang Wu , Yi Yang , Defu Lian , Enhong Chen

Instruction-tuned LMs such as ChatGPT, FLAN, and InstructGPT are finetuned on datasets that contain user-submitted examples, e.g., FLAN aggregates numerous open-source datasets and OpenAI leverages examples submitted in the browser…

Computation and Language · Computer Science 2023-05-02 Alexander Wan , Eric Wallace , Sheng Shen , Dan Klein