Related papers: General Framework for Reversible Data Hiding in Te…
Distributional word vectors have recently been shown to encode many of the human biases, most notably gender and racial biases, and models for attenuating such biases have consequently been proposed. However, existing models and studies (1)…
This paper presents a reversible data hiding in encrypted image that employs based notions of the RDH in plain-image schemes including histogram modification and prediction-error computation. In the proposed method, original image may be…
With the advancement of large-scale language modeling techniques, large multimodal models combining visual encoders with large language models have demonstrated exceptional performance in various visual tasks. Most of the current…
Bilingual word embeddings have been widely used to capture the similarity of lexical semantics in different human languages. However, many applications, such as cross-lingual semantic search and question answering, can be largely benefited…
In recent years, reversible data hiding has attracted much more attention than before. Reversibility signifies that the original media can be recovered without any loss from the marked media after extracting the embedded message. This paper…
As a technology that can prevent the information from being disclosed, the reversible data hiding in encrypted images (RDHEI) acts as an important role in privacy protection and information security. To make use of the image redundancy and…
Textual grounding is an important but challenging task for human-computer interaction, robotics and knowledge mining. Existing algorithms generally formulate the task as selection from a set of bounding box proposals obtained from deep net…
From extracting features to generating text, the outputs of large language models (LLMs) typically rely on the final layers, following the conventional wisdom that earlier layers capture only low-level cues. However, our analysis shows that…
Recently, with the help of deep learning models, significant advances have been made in different Natural Language Processing (NLP) tasks. Unfortunately, state-of-the-art models are vulnerable to noisy texts. We propose a new contextual…
Large language models (LLMs) have achieved remarkable progress across diverse tasks, yet their internal mechanisms remain largely opaque. In this work, we investigate a fundamental question: to what extent can the original input text be…
This paper develops a model that addresses sentence embedding, a hot topic in current natural language processing research, using recurrent neural networks with Long Short-Term Memory (LSTM) cells. Due to its ability to capture long term…
This paper presents a survey of text steganography methods used for hid- ing secret information inside some covertext. Widely known hiding techniques (such as translation based steganography, text generating and syntactic embed- ding) and…
Machine learning models have been shown to inherit biases from their training datasets. This can be particularly problematic for vision-language foundation models trained on uncurated datasets scraped from the internet. The biases can be…
Recent years have seen an increasing emphasis on information security, and various encryption methods have been proposed. However, for symmetric encryption methods, the well-known encryption techniques still rely on the key space to…
The task of text privatization using Differential Privacy has recently taken the form of $\textit{text rewriting}$, in which an input text is obfuscated via the use of generative (large) language models. While these methods have shown…
Word embeddings allow natural language processing systems to share statistical information across related words. These embeddings are typically based on distributional statistics, making it difficult for them to generalize to rare or unseen…
Data representation is a fundamental task in machine learning. The representation of data affects the performance of the whole machine learning system. In a long history, the representation of data is done by feature engineering, and…
Besides the text content, documents and their associated words usually come with rich sets of meta informa- tion, such as categories of documents and semantic/syntactic features of words, like those encoded in word embeddings. Incorporating…
In this paper, we suggest a novel data hiding technique in an HTML Web page. HTML Tags are case insensitive and hence an alphabet in lowercase and one in uppercase present inside an HTML tag are interpreted in the same manner by the…
With widening deployments of natural language processing (NLP) in daily life, inherited social biases from NLP models have become more severe and problematic. Previous studies have shown that word embeddings trained on human-generated…