相关论文: Towards Robust and Privacy-preserving Text Represe…

Text-to-image diffusion models have demonstrated remarkable capabilities in creating images highly aligned with user prompts, yet their proclivity for memorizing training set images has sparked concerns about the originality of the…

We study the privatization of distributed learning and optimization strategies. We focus on differential privacy schemes and study their effect on performance. We show that the popular additive random perturbation scheme degrades…

Data used to train machine learning models can be adversarial--maliciously constructed by adversaries to fool the model. Challenge also arises by privacy, confidentiality, or due to legal constraints when data are geographically gathered…

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…

Recent advancements in large language models (LLMs) have been fueled by large scale training corpora drawn from diverse sources such as websites, news articles, and books. These datasets often contain explicit user information, such as…

Accurately learning from user data while providing quantifiable privacy guarantees provides an opportunity to build better ML models while maintaining user trust. This paper presents a formal approach to carrying out privacy preserving text…

Text mining and information retrieval techniques have been developed to assist us with analyzing, organizing and retrieving documents with the help of computers. In many cases, it is desirable that the authors of such documents remain…

Many models are pretrained on redacted text for privacy reasons. Clinical foundation models are often trained on de-identified text, which uses special syntax (masked) text in place of protected health information. Even though these models…

Authorship analysis is an important subject in the field of natural language processing. It allows the detection of the most likely writer of articles, news, books, or messages. This technique has multiple uses in tasks related to…

Differentially-private mechanisms for text generation typically add carefully calibrated noise to input words and use the nearest neighbor to the noised input as the output word. When the noise is small in magnitude, these mechanisms are…

The current privacy evaluation for speaker anonymization often overestimates privacy when a same-gender target selection algorithm (TSA) is used, although this TSA leaks the speaker's gender and should hence be more vulnerable. We…

Ensuring the privacy of sensitive data used to train modern machine learning models is of paramount importance in many areas of practice. One approach to study these concerns is through the lens of differential privacy. In this framework,…

Existing privacy-preserving speech representation learning methods target a single application domain. In this paper, we present a novel framework to anonymize utterance-level speech embeddings generated by pre-trained encoders and show its…

Pretraining techniques leveraging enormous datasets have driven recent advances in text summarization. While folk explanations suggest that knowledge transfer accounts for pretraining's benefits, little is known about why it works or what…

In this paper, we study the problem of deceptive reinforcement learning to preserve the privacy of a reward function. Reinforcement learning is the problem of finding a behaviour policy based on rewards received from exploratory behaviour.…

Automatic speech recognition (ASR) is a key technology in many services and applications. This typically requires user devices to send their speech data to the cloud for ASR decoding. As the speech signal carries a lot of information about…

Anonymizing text that contains sensitive information is crucial for a wide range of applications. Existing techniques face the emerging challenges of the re-identification ability of large language models (LLMs), which have shown advanced…

Large language models (LLMs) have significantly transformed natural language understanding and generation, but they raise privacy concerns due to potential exposure of sensitive information. Studies have highlighted the risk of information…

We show that while anonymization effectively obscures firm identity, it significantly reduces the power of textual understanding, thereby diminishing models' ability to extract meaningful economic signals from financial texts. This…

Recent advances in neural network based language models lead to successful deployments of such models, improving user experience in various applications. It has been demonstrated that strong performance of language models comes along with…