Cybersecurity professionals need hands-on training to prepare for managing the current advanced cyber threats. To practice cybersecurity skills, training participants use numerous software tools in computer-supported interactive learning environments to perform offensive or defensive actions. The interaction involves typing commands, communicating over the network, and engaging with the training environment. The training artifacts (data resulting from this interaction) can be highly beneficial in educational research. For example, in cybersecurity education, they provide insights into the trainees' learning processes and support effective learning interventions. However, this research area is not yet well-understood. Therefore, this paper surveys publications that enhance cybersecurity education by leveraging trainee-generated data from interactive learning environments. We identified and examined 3021 papers, ultimately selecting 35 articles for a detailed review. First, we investigated which data are employed in which areas of cybersecurity training, how, and why. Second, we examined the applications and impact of research in this area, and third, we explored the community of researchers. Our contribution is a systematic literature review of relevant papers and their categorization according to the collected data, analysis methods, and application contexts. These results provide researchers, developers, and educators with an original perspective on this emerging topic. To motivate further research, we identify trends and gaps, propose ideas for future work, and present practical recommendations. Overall, this paper provides in-depth insight into the recently growing research on collecting and analyzing data from hands-on training in security contexts.
相關內容
IFIP TC13 Conference on Human-Computer Interaction是人機交互領域的研究者和實踐者展示其工作的重要平臺。多年來，這些會議吸引了來自幾個國家和文化的研究人員。官網鏈接： ·
估計/估計量
·
MoDELS
·
可約的
·
Processing（編程語言）
·
Large Language Models (LLMs) have revolutionized Natural Language Processing (NLP). Although convenient for research and practical applications, open-source LLMs with fewer parameters often suffer from severe hallucinations compared to their larger counterparts. This paper focuses on measuring and reducing hallucinations in BLOOM 7B, a representative of such weaker open-source LLMs that are publicly available for research and commercial applications. We introduce HaloCheck, a lightweight BlackBox knowledge-free framework designed to quantify the severity of hallucinations in LLMs. Additionally, we explore techniques like knowledge injection and teacher-student approaches to alleviate hallucinations in low-parameter LLMs. Our experiments effectively demonstrate the reduction of hallucinations in challenging domains for these LLMs.
Variability constraints are an integral part of the requirements for a configurable system. The constraints specified in the requirements on the legal combinations of options define the space of potential valid configurations for the system-to-be. This paper reports on our experience with the variability-related requirements constraints of a flight software framework used by multiple space missions. A challenge that we saw for practitioners using the current framework, now open-sourced, is that the specifications of its variability-related requirements and constraints are dispersed across several documents, rather than being centralized in the software requirements specification. Such dispersion can contribute to misunderstandings of the side-effects of design choices, increased effort for developers, and bugs during operations. Based on our experience, we propose a new software variability model, similar to a product-line feature model, in the flight software framework. We describe the structured technique by which our model is developed, demonstrate its use, and evaluate it on a key service module of the flight software. Results show that our lightweight modeling technique helped find missing and inconsistent variability-related requirements and constraints. More generally, we suggest that a variability modeling technique such as this can be an efficient way for developers to centralize the specification and improve the analysis of dispersed variability-related requirements and constraints in other configurable systems.
We study stochastic Cubic Newton methods for solving general possibly non-convex minimization problems. We propose a new framework, which we call the helper framework, that provides a unified view of the stochastic and variance-reduced second-order algorithms equipped with global complexity guarantees. It can also be applied to learning with auxiliary information. Our helper framework offers the algorithm designer high flexibility for constructing and analyzing the stochastic Cubic Newton methods, allowing arbitrary size batches, and the use of noisy and possibly biased estimates of the gradients and Hessians, incorporating both the variance reduction and the lazy Hessian updates. We recover the best-known complexities for the stochastic and variance-reduced Cubic Newton, under weak assumptions on the noise. A direct consequence of our theory is the new lazy stochastic second-order method, which significantly improves the arithmetic complexity for large dimension problems. We also establish complexity bounds for the classes of gradient-dominated objectives, that include convex and strongly convex problems. For Auxiliary Learning, we show that using a helper (auxiliary function) can outperform training alone if a given similarity measure is small.
A recent empirical observation of activation sparsity in MLP layers offers an opportunity to drastically reduce computation costs for free. Despite several works attributing it to training dynamics, the theoretical explanation of activation sparsity's emergence is restricted to shallow networks, small training steps well as modified training, even though the sparsity has been found in deep models trained by vanilla protocols for large steps. To fill the three gaps, we propose the notion of gradient sparsity as the source of activation sparsity and a theoretical explanation based on it that explains gradient sparsity and then activation sparsity as necessary steps to adversarial robustness w.r.t. hidden features and parameters, which is approximately the flatness of minima for well-learned models. The theory applies to standardly trained LayerNorm-ed pure MLPs, and further to Transformers or other architectures if noises are added to weights during training. To eliminate other sources of flatness when arguing sparsities' necessity, we discover the phenomenon of spectral concentration, i.e., the ratio between the largest and the smallest non-zero singular values of weight matrices is small. We utilize random matrix theory (RMT) as a powerful theoretical tool to analyze stochastic gradient noises and discuss the emergence of spectral concentration. With these insights, we propose two plug-and-play modules for both training from scratch and sparsity finetuning, as well as one radical modification that only applies to from-scratch training. Another under-testing module for both sparsity and flatness is also immediate from our theories. Validational experiments are conducted to verify our explanation. Experiments for productivity demonstrate modifications' improvement in sparsity, indicating further theoretical cost reduction in both training and inference.
Thermodynamic equations of state (EOS) are essential for many industries as well as in academia. Even leaving aside the expensive and extensive measurement campaigns required for the data acquisition, the development of EOS is an intensely time-consuming process, which does often still heavily rely on expert knowledge and iterative fine-tuning. To improve upon and accelerate the EOS development process, we introduce thermodynamics-informed symbolic regression (TiSR), a symbolic regression (SR) tool aimed at thermodynamic EOS modeling. TiSR is already a capable SR tool, which was used in the research of //doi.org/10.1007/s10765-023-03197-z. It aims to combine an SR base with the extensions required to work with often strongly scattered experimental data, different residual pre- and post-processing options, and additional features required to consider thermodynamic EOS development. Although TiSR is not ready for end users yet, this paper is intended to report on its current state, showcase the progress, and discuss (distant and not so distant) future directions. TiSR is available at //github.com/scoop-group/TiSR and can be cited as //doi.org/10.5281/zenodo.8317547.
We introduce a general framework for measuring acoustic properties such as liner time-invariant (LTI) response, signal-dependent time-invariant (SDTI) component, and random and time-varying (RTV) component simultaneously using structured periodic test signals. The framework also enables music pieces and other sound materials as test signals by "safeguarding" them by adding slight deterministic "noise." Measurement using swept-sin, MLS (Maxim Length Sequence), and their variants are special cases of the proposed framework. We implemented interactive and real-time measuring tools based on this framework and made them open-source. Furthermore, we applied this framework to assess pitch extractors objectively.
Unmeasured confounding bias is among the largest threats to the validity of observational studies. Although sensitivity analyses and various study designs have been proposed to address this issue, they do not leverage the growing availability of auxiliary data accessible through open data platforms. Using negative controls has been introduced in the causal inference literature as a promising approach to account for unmeasured confounding bias. In this paper, we develop a Bayesian nonparametric method to estimate a causal exposure-response function (CERF). This estimation method effectively utilizes auxiliary information from negative control variables to adjust for unmeasured confounding completely. We model the CERF as a mixture of linear models. This strategy offers the dual advantage of capturing the potential nonlinear shape of CERFs while maintaining computational efficiency. Additionally, it leverages closed-form results that hold under the linear model assumption. We assess the performance of our method through simulation studies. The results demonstrate the method's ability to accurately recover the true shape of the CERF in the presence of unmeasured confounding. To showcase the practical utility of our approach, we apply it to adjust for a potential unmeasured confounder when evaluating the relationship between long-term exposure to ambient $PM_{2.5}$ and cardiovascular hospitalization rates among the elderly in the continental U.S. We implement our estimation procedure in open-source software to ensure transparency and reproducibility and make our code publicly available.
Traumatic brain injury (TBI) can cause cognitive, communication, and psychological challenges that profoundly limit independence in everyday life. Conversational Agents (CAs) can provide individuals with TBI with cognitive and communication support, although little is known about how they make use of CAs to address injury-related needs. In this study, we gave nine adults with TBI an at-home CA for four weeks to investigate use patterns, challenges, and design requirements, focusing particularly on injury-related use. The findings revealed significant gaps between the current capabilities of CAs and accessibility challenges faced by TBI users. We also identified 14 TBI-related activities that participants engaged in with CAs. We categorized those activities into four groups: mental health, cognitive activities, healthcare and rehabilitation, and routine activities. Design implications focus on accessibility improvements and functional designs of CAs that can better support the day-to-day needs of people with TBI.
Pre-trained Language Models (PLMs) which are trained on large text corpus via self-supervised learning method, have yielded promising performance on various tasks in Natural Language Processing (NLP). However, though PLMs with huge parameters can effectively possess rich knowledge learned from massive training text and benefit downstream tasks at the fine-tuning stage, they still have some limitations such as poor reasoning ability due to the lack of external knowledge. Research has been dedicated to incorporating knowledge into PLMs to tackle these issues. In this paper, we present a comprehensive review of Knowledge-Enhanced Pre-trained Language Models (KE-PLMs) to provide a clear insight into this thriving field. We introduce appropriate taxonomies respectively for Natural Language Understanding (NLU) and Natural Language Generation (NLG) to highlight these two main tasks of NLP. For NLU, we divide the types of knowledge into four categories: linguistic knowledge, text knowledge, knowledge graph (KG), and rule knowledge. The KE-PLMs for NLG are categorized into KG-based and retrieval-based methods. Finally, we point out some promising future directions of KE-PLMs.
Despite its great success, machine learning can have its limits when dealing with insufficient training data. A potential solution is the additional integration of prior knowledge into the training process which leads to the notion of informed machine learning. In this paper, we present a structured overview of various approaches in this field. We provide a definition and propose a concept for informed machine learning which illustrates its building blocks and distinguishes it from conventional machine learning. We introduce a taxonomy that serves as a classification framework for informed machine learning approaches. It considers the source of knowledge, its representation, and its integration into the machine learning pipeline. Based on this taxonomy, we survey related research and describe how different knowledge representations such as algebraic equations, logic rules, or simulation results can be used in learning systems. This evaluation of numerous papers on the basis of our taxonomy uncovers key methods in the field of informed machine learning.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191