Related papers: Generating Memorable Mnemonic Encodings of Numbers

Strong passwords are fundamental to the security of password-based user authentication systems. In recent years, much effort has been made to evaluate password strength or to generate strong passwords. Unfortunately, the usability or…

Text-based secrets are still the most commonly used authentication mechanism in information systems. IT managers must strike a balance between security and memorability while developing password policies. Initially introduced as more secure…

Large language models (LLMs) have exhibited impressive competence in various tasks, but their internal mechanisms on mathematical problems are still under-explored. In this paper, we study a fundamental question: how language models encode…

Weak passwords and availability of supercomputers to password crackers make the financial institutions and businesses at stake. This calls for use of strong passwords and multi factor authentication for secure transactions. Remembering a…

Sentence embeddings are commonly used in text clustering and semantic retrieval tasks. State-of-the-art sentence representation methods are based on artificial neural networks fine-tuned on large collections of manually labeled sentence…

Over-parameterized neural language models (LMs) can memorize and recite long sequences of training data. While such memorization is normally associated with undesired properties such as overfitting and information leaking, our work casts…

Memorization is a fundamental ability of Transformer-based Large Language Models, achieved through learning. In this paper, we propose a paradigm shift by designing an architecture to memorize text directly, bearing in mind the principle…

An important component of achieving language understanding is mastering the composition of sentence meaning, but an immediate challenge to solving this problem is the opacity of sentence vector representations produced by current neural…

In second language vocabulary learning, existing works have primarily focused on either the learning interface or scheduling personalized retrieval practices to maximize memory retention. However, the learning content, i.e., the information…

Large Language Models (LLMs), trained on massive corpora with billions of parameters, show unprecedented performance in various fields. Though surprised by their excellent performances, researchers also noticed some special behaviors of…

Keyphrase provides highly-condensed information that can be effectively used for understanding, organizing and retrieving text content. Though previous studies have provided many workable solutions for automated keyphrase extraction, they…

Phrases play an important role in natural language understanding and machine translation (Sag et al., 2002; Villavicencio et al., 2005). However, it is difficult to integrate them into current neural machine translation (NMT) which reads…

In recent years, the widespread application of large language models has inspired us to consider using inference for communication encryption. We therefore propose CipherMind, which utilizes intermediate results from deterministic…

We study a class of neuro-symbolic generative models in which neural networks are used both for inference and as priors over symbolic, data-generating programs. As generative models, these programs capture compositional structures in a…

The ability of machine learning models to store input information in hidden layer vector embeddings, analogous to the concept of `memory', is widely employed but not well characterized. We find that language model embeddings typically…

In this paper, we introduce personalized word embeddings, and examine their value for language modeling. We compare the performance of our proposed prediction model when using personalized versus generic word representations, and study how…

Modern Neural Machine Translation systems exhibit strong performance in several different languages and are constantly improving. Their ability to learn continuously is, however, still severely limited by the catastrophic forgetting issue.…

Password guessing approaches via deep learning have recently been investigated with significant breakthroughs in their ability to generate novel, realistic password candidates. In the present work we study a broad collection of deep…

In this paper, we study an under-explored area of language and vocabulary learning: keyword mnemonics, a technique for memorizing vocabulary through memorable associations with a target word via a verbal cue. Typically, creating verbal cues…

Personal Identification Numbers (PINs) are commonly used as an authentication mechanism. An important security requirement is that PINs should be hard to guess for an attacker. On the other hand, remembering several random PINs can be…