Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userPassFlow: Guessing Passwords with Generative Flows
70
0
0.0
(
0
)
Added by
Dorjan Hitaj
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Recent advances in generative machine learning models rekindled research interest in the area of password guessing. Data-driven password guessing approaches based on GANs, language models and deep latent variable models show impressive generalization performance and offer compelling properties for the task of password guessing. In this paper, we propose a flow-based generative model approach to password guessing. Flow-based models allow for precise log-likelihood computation and optimization, which enables exact latent variable inference. Additionally, flow-based models provide meaningful latent space representation, which enables operations such as exploration of specific subspaces of the latent space and interpolation. We demonstrate the applicability of generative flows to the context of password guessing, departing from previous applications of flow networks which are mainly limited to the continuous space of image generation. We show that the above-mentioned properties allow flow-based models to outperform deep latent variable model approaches and remain competitive with state-of-the-art GANs in the password guessing task, while using a training set that is orders of magnitudes smaller than that of previous art. Furthermore, a qualitative analysis of the generated samples shows that flow-based networks are able to accurately model the original passwords distribution, with even non-matched samples closely resembling human-like passwords.
rate research
Read More
State-of-the-art password guessing tools, such as HashCat and John the Ripper, enable users to check billions of passwords per second against password hashes. In addition to performing straightforward dictionary attacks, these tools can expand password dictionaries using password generation rules, such as concatenation of words (e.g., password123456) and leet speak (e.g., password becomes p4s5w0rd). Although these rules work well in practice, expanding them to model further passwords is a laborious task that requires specialized expertise. To address this issue, in this paper we introduce PassGAN, a novel approach that replaces human-generated password rules with theory-grounded machine learning algorithms. Instead of relying on manual password analysis, PassGAN uses a Generative Adversarial Network (GAN) to autonomously learn the distribution of real passwords from actual password leaks, and to generate high-quality password guesses. Our experiments show that this approach is very promising. When we evaluated PassGAN on two large password datasets, we were able to surpass rule-based and state-of-the-art machine learning password guessing tools. However, in contrast with the other tools, PassGAN achieved this result without any a-priori knowledge on passwords or common password structures. Additionally, when we combined the output of PassGAN with the output of HashCat, we were able to match 51%-73% more passwords than with HashCat alone. This is remarkable, because it shows that PassGAN can autonomously extract a considerable number of password properties that current state-of-the art rules do not encode.
We describe a password generation scheme based on Markov models built from English text (specifically, Charles Dickens *A Tale Of Two Cities*). We show a (linear-running-time) bijection between random bitstrings of any desired length and generated text, ensuring that all passwords are generated with equal probability. We observe that the generated passwords appear to strike a reasonable balance between memorability and security. Using the system, we get 56-bit passwords like The cusay is wither? t, rather than passwords like tQ$%Xc4Ef.
Flow-based generative models have shown excellent ability to explicitly learn the probability density function of data via a sequence of invertible transformations. Yet, modeling long-range dependencies over normalizing flows remains understudied. To fill the gap, in this paper, we introduce two types of invertible attention mechanisms for generative flow models. To be precise, we propose map-based and scaled dot-product attention for unconditional and conditional generative flow models. The key idea is to exploit split-based attention mechanisms to learn the attention weights and input representations on every two splits of flow feature maps. Our method provides invertible attention modules with tractable Jacobian determinants, enabling seamless integration of it at any positions of the flow-based models. The proposed attention mechanism can model the global data dependencies, leading to more comprehensive flow models. Evaluation on multiple generation tasks demonstrates that the introduced attention flow idea results in efficient flow models and compares favorably against the state-of-the-art unconditional and conditional generative flow methods.
In recent decades, criminals have increasingly used the web to research, assist and perpetrate criminal behaviour. One of the most important ways in which law enforcement can battle this growing trend is through accessing pertinent information about suspects in a timely manner. A significant hindrance to this is the difficulty of accessing any system a suspect uses that requires authentication via password. Password guessing techniques generally consider common user behaviour while generating their passwords, as well as the password policy in place. Such techniques can offer a modest success rate considering a large/average population. However, they tend to fail when focusing on a single target -- especially when the latter is an educated user taking precautions as a savvy criminal would be expected to do. Open Source Intelligence is being increasingly leveraged by Law Enforcement in order to gain useful information about a suspect, but very little is currently being done to integrate this knowledge in an automated way within password cracking. The purpose of this research is to delve into the techniques that enable the gathering of the necessary context about a suspect and find ways to leverage this information within password guessing techniques.
In this work, we formally study the membership privacy risk of generative models and propose a membership privacy estimation framework. We formulate the membership privacy risk as a statistical divergence between training samples and hold-out samples, and propose sample-based methods to estimate this divergence. Unlike previous works, our proposed metric and estimators make realistic and flexible assumptions. First, we offer a generalizable metric as an alternative to accuracy for imbalanced datasets. Second, our estimators are capable of estimating the membership privacy risk given any scalar or vector valued attributes from the learned model, while prior work require access to specific attributes. This allows our framework to provide data-driven certificates for trained generative models in terms of membership privacy risk. Finally, we show a connection to differential privacy, which allows our proposed estimators to be used to understand the privacy budget epsilon needed for differentially private generative models. We demonstrate the utility of our framework through experimental demonstrations on different generative models using various model attributes yielding some new insights about membership leakage and vulnerabilities of models.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
