Related papers: Interpretable Probabilistic Password Strength Mete…

Security questions are one of the mechanisms used to recover passwords. Strong answers to security questions (i.e. high entropy) are hard for attackers to guess or obtain using social engineering techniques (e.g. monitoring of social…

The majority of research in computational psycholinguistics has concentrated on the processing of words. This study introduces innovative methods for computing sentence-level metrics using multilingual large language models. The metrics…

Passwords should be easy to remember, yet expiration policies mandate their frequent change. Caught in the crossfire between these conflicting requirements, users often adopt creative methods to perform slight variations over time. While…

The successful application of machine learning (ML) methods becomes increasingly dependent on their interpretability or explainability. Designing explainable ML systems is instrumental to ensuring transparency of automated decision-making…

Large Language Models (LLMs) are increasingly vulnerable to adversarial attacks that can subtly manipulate their outputs. While various defense mechanisms have been proposed, many operate as black boxes, lacking transparency in their…

Password authentication is a very important system security procedure to gain access to user resources. In the Traditional password authentication methods a server has check the authenticity of the users. In our proposed method users can…

The emergence of large-scale pretrained language models has posed unprecedented challenges in deriving explanations of why the model has made some predictions. Stemmed from the compositional nature of languages, spurious correlations have…

Vulnerabilities related to weak passwords are a pressing global economic and security issue. We report a novel, simple, and effective approach to address the weak password problem. Building upon chaotic dynamics, criticality at phase…

As machine learning algorithms getting adopted in an ever-increasing number of applications, interpretation has emerged as a crucial desideratum. In this paper, we propose a mathematical definition for the human-interpretable model. In…

Honeyword is a representative "honey" technique that employs decoy objects to mislead adversaries and protect the real ones. To assess the security of a Honeyword system, two metrics--flatness and success-number--have been proposed and…

Mechanistic interpretability is the program of explaining what AI systems are doing in terms of their internal mechanisms. I analyze some aspects of the program, along with setting out some concrete challenges and assessing progress to…

Robust verbal confidence generated by large language models (LLMs) is crucial for the deployment of LLMs to help ensure transparency, trust, and safety in many applications, including those involving human-AI interactions. In this paper, we…

People judge interactions with large language models (LLMs) as successful when outputs match what they want, not what they type. Yet LLMs are trained to predict the next token solely from text input, not underlying intent. Because written…

Password authentication suffers from the well-known tradeoff between security and usability. Secure passwords are difficult for users to remember, and memorable passwords are often easy to guess. SPARse Two-dimensional AuthenticatioN…

Recent research has recognized interpretability and robustness as essential properties of trustworthy classification. Curiously, a connection between robustness and interpretability was empirically observed, but the theoretical reasoning…

Implicit authentication consists of a server authenticating a user based on the user's usage profile, instead of/in addition to relying on something the user explicitly knows (passwords, private keys, etc.). While implicit authentication…

Previous research on word embeddings has shown that sparse representations, which can be either learned on top of existing dense embeddings or obtained through model constraints during training time, have the benefit of increased…

Recently, adversarial deception becomes one of the most considerable threats to deep neural networks. However, compared to extensive research in new designs of various adversarial attacks and defenses, the neural networks' intrinsic…

Probabilistic programming (PP) is a programming paradigm that allows for writing statistical models like ordinary programs, performing simulations by running those programs, and analyzing and refining their statistical behavior using…

Although there have been many solutions applied, the safety challenges related to the password security mechanism are not reduced. The reason for this is that while the means and tools to support password attacks are becoming more and more…