ABSTRACT Spider silk has exceptional mechanical properties, notably its high toughness, which is a measure of a material's ability to absorb energy before failure. Predicting toughness using physical, biochemical, and genetic features is a challenging task due to the nonlinear and multivariate interactions involved. This study presents a comprehensive machine learning framework to predict the toughness and the tensile strength of spider silk fibers using interpretable and high‐performing models. A curated dataset with varied physicochemical and structural features was used to train, tune, and evaluate multiple machine learning models, including Decision Tree, support vector machines, Random Forest, Gradient Boosting, and XGBoost. Feature engineering steps introduced domain‐specific constructs such as a toughness proxy and modulus transformations. Hyperparameter tuning was conducted via Bayesian optimization to enhance model performance. Among all tested models, the tuned XGBoost regressor achieved the highest predictive accuracy ( and 0.765), outperforming all other models. Feature importance analysis highlighted several key predictors among Young's modulus, aligning with known biological mechanisms for both toughness and tensile strength. This work demonstrates how machine learning can be used not only for accurate prediction but also to uncover the underlying determinants of silk toughness. The proposed framework sets the stage for data‐driven design of bioinspired synthetic fibers and represents a significant step toward the computational modeling of high‐performance biomaterials.

Abstract Axial spondyloarthritis (SpA) is an inflammatory disease that causes back pain by affecting the axial skeleton, and the sacroiliac (SI) joints are mostly involved. An early diagnosis is required to prevent structural damage. Magnetic resonance imaging (MRI) is the primary tool for the diagnosis of axial spondyloarthritis; however, the occurrence of noninflammatory degenerative changes might prevent the accurate diagnosis even for experts. Deep learning (DL) aims to assist radiologists in detecting and diagnosing sacroiliitis by providing distinct and effective feature extraction along MR sequences. This retrospective study considers a primary dataset with 50 clinical sacroiliitis and 50 control group patients and aims to diagnose sacroiliitis using 4 MRI sequences. For this purpose, a simplified convolutional neural network model is developed, and comprehensive comparative experiments and analyses are performed. Three pre-trained DL models are considered in a comparative study using a transfer learning approach. Image-based, sequence-based, and patient-based experiments are conducted to evaluate general diagnostic abilities, analyze further clinical implementations, and determine the most informative and challenging MRI sequences. The results showed that the proposed model has the ability to detect sacroiliitis with 0.951 and 0.977 accuracy in patient and image-based experiments, respectively. The deep learning models obtained promising results for future clinical implementation to assist radiologists in detecting sacroiliitis. It is also analyzed that the STIR coronal images are the most challenging, while T1 axial sequences are the most informative sequences for sacroiliitis diagnosis.

In the pursuit of an effective spam detection system, the focus has often been on identifying known spam patterns either through rule-based detection systems or machine learning (ML) solutions that rely on keywords. However, both systems are susceptible to evasion techniques and zero-day attacks that can be achieved at low cost. Therefore, an email that bypassed the defense system once can do it again in the following days, even though rules are updated or the ML models are retrained. The recurrence of failures to detect emails that exhibit layout similarities to previously undetected spam is concerning for customers and can erode their trust in a company. Our observations show that threat actors reuse email kits extensively and can bypass detection with little effort, for example, by making changes to the content of emails. In this work, we propose an email visual similarity detection approach, named Pisco, to improve the detection capabilities of an email threat defense system. We apply our proof of concept to some real-world samples received from different sources. Our results show that email kits are being reused extensively and visually similar emails are sent to our customers at various time intervals. Therefore, this method could be very helpful in situations where detection engines that rely on textual features and keywords are bypassed, an occurrence our observations show happens frequently.

Assigning family labels to malicious apps is a common practice for grouping together malware with identical behavior. However, recent studies show that apps labeled as belonging to the same family do not necessarily behave similarly: one app may lack or have extra capabilities compared to others in the same family, and, conversely, two apps labeled as belonging to different families may exhibit close behavior. To reveal these inconsistencies, this paper presents AndrEnsemble, a characterization system for Android malware families based on ensembles of sensitive API calls extracted from aggregated call graphs of different families. Our method has several advantages over similar characterization approaches, including a greater reduction ratio with respect to original call graphs, robustness against transformation attacks, and flexibility to be applied at different granularity levels. We experimentally validate our approach and discuss three specific use cases: mobile ransomware, SMS Trojans and banking Trojans. This left us with some interesting findings. First of all, malicious operations in these types of malware are not necessarily exercised by using several sensitive API calls all together. Second, SMS Trojans have larger ensembles of API calls compared to the other types. Last but not least, we identified several samples with identical ensembles though being labeled as part of different families.

Obfuscation techniques modify an app’s source (or machine) code in order to make it more difficult to analyze. This is typically applied to protect intellectual property in benign apps, or to hinder the process of extracting actionable information in the case malware. Since malware analysis often requires considerable resource investment, detecting the particular obfuscation technique used may contribute to apply the right analysis tools, thus leading to some savings. In this paper, we propose AndrODet , a mechanism to detect three popular types of obfuscation in Android applications, namely identifier renaming, string encryption, and control flow obfuscation. AndrODet leverages online learning techniques, thus being suitable for resource-limited environments that need to operate in a continuous manner. We compare our results with a batch learning algorithm using a dataset of 34,962 apps from both malware and benign apps. Experimental results show that online learning approaches are not only able to compete with batch learning methods in terms of accuracy, but they also save significant amount of time and computational resources. Particularly, AndrODet achieves an accuracy of 92.02% for identifier renaming detection, 81.41% for string encryption detection, and 68.32% for control flow obfuscation detection, on average. Also, the overall accuracy of the system when apps might be obfuscated with more than one technique is around 80.66%.

Information flows in Android can be effectively used to give an informative summary of an application's behavior, showing how and for what purpose apps use specific pieces of information. This has been shown to be extremely useful to characterize risky behaviors and, ultimately, to identify unwanted or malicious applications in Android. However, identifying information flows in an application is computationally highly expensive and, with more than one million apps in the Google Play market, it is critical to prioritize applications that are likely to pose a risk. In this work, we develop a triage mechanism to rank applications considering their potential risk. Our approach, called TriFlow, relies on static features that are quick to obtain. TriFlow combines a probabilistic model to predict the existence of information flows with a metric of how significant a flow is in benign and malicious apps. Based on this, TriFlow provides a score for each application that can be used to prioritize analysis. TriFlow also provides an explanatory report of the associated risk. We evaluate our tool with a representative dataset of benign and malicious Android apps. Our results show that it can predict the presence of information flows very accurately and that the overall triage mechanism enables significant resource saving.