相关论文: Killing One Bird with Two Stones: Model Extraction…

The collection and availability of big data, combined with advances in pre-trained models (e.g. BERT), have revolutionized the predictive performance of natural language processing tasks. This allows corporations to provide machine learning…

Natural language processing (NLP) tasks, ranging from text classification to text generation, have been revolutionised by the pre-trained language models, such as BERT. This allows corporations to easily build powerful APIs by encapsulating…

We study the problem of model extraction in natural language processing, in which an adversary with only query access to a victim model attempts to reconstruct a local copy of that model. Assuming that both the adversary and victim model…

Pre-trained large language models, such as GPT\nobreakdash-2 and BERT, are often fine-tuned to achieve state-of-the-art performance on a downstream task. One natural example is the ``Smart Reply'' application where a pre-trained model is…

Model extraction attacks pose significant security threats to deployed language models, potentially compromising intellectual property and user privacy. This survey provides a comprehensive taxonomy of LLM-specific extraction attacks and…

Adversarial attacks for discrete data (such as texts) have been proved significantly more challenging than continuous data (such as images) since it is difficult to generate adversarial samples with gradient-based methods. Current…

Machine learning (ML) models have significantly grown in complexity and utility, driving advances across multiple domains. However, substantial computational resources and specialized expertise have historically restricted their wide…

With an increase in low-cost machine learning APIs, advanced machine learning models may be trained on private datasets and monetized by providing them as a service. However, privacy researchers have demonstrated that these models may leak…

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…

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…

Model extraction increasingly attracts research attentions as keeping commercial AI models private can retain a competitive advantage. In some scenarios, AI models are trained proprietarily, where neither pre-trained models nor sufficient…

Recent studies have shown that large language models (LLMs) can infer private user attributes (e.g., age, location, gender) from user-generated text shared online, enabling rapid and large-scale privacy breaches. Existing…

Model extraction (ME) attacks represent one major threat to Machine-Learning-as-a-Service (MLaaS) platforms by ``stealing'' the functionality of confidential machine-learning models through querying black-box APIs. Over seven years have…

Model explanations provide transparency into a trained machine learning model's blackbox behavior to a model builder. They indicate the influence of different input attributes to its corresponding model prediction. The dependency of…

Privacy preserving deep learning is an emerging field in machine learning that aims to mitigate the privacy risks in the use of deep neural networks. One such risk is training data extraction from language models that have been trained on…

Machine learning (ML) has become a core component of many real-world applications and training data is a key factor that drives current progress. This huge success has led Internet companies to deploy machine learning as a service (MLaaS).…

It has become common to publish large (billion parameter) language models that have been trained on private datasets. This paper demonstrates that in such settings, an adversary can perform a training data extraction attack to recover…

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…

As machine learning (ML) technologies become more prevalent in privacy-sensitive areas like healthcare and finance, eventually incorporating sensitive information in building data-driven algorithms, it is vital to scrutinize whether these…

Adversarial attacks expose important blind spots of deep learning systems. While word- and sentence-level attack scenarios mostly deal with finding semantic paraphrases of the input that fool NLP models, character-level attacks typically…