Active Learning (AL) for Hyperspectral Image Classification (HSIC) has been extensively studied. However, the traditional AL methods do not consider randomness among the existing and new samples. Secondly, very limited AL research has been carried out on joint spectral–spatial information. Thirdly, a minor but still worth mentioning factor is the stopping criteria. Therefore, this study caters to all these issues using a spatial prior Fuzziness concept coupled with Multinomial Logistic Regression via a Splitting and Augmented Lagrangian (MLR-LORSAL) classifier with dual stopping criteria. This work further compares several sample selection methods with the diverse nature of classifiers i.e., probabilistic and non-probabilistic. The sample selection methods include Breaking Ties (BT), Mutual Information (MI) and Modified Breaking Ties (MBT). The comparative classifiers include Support Vector Machine (SVM), Extreme Learning Machine (ELM), K-Nearest Neighbour (KNN) and Ensemble Learning (EL). The experimental results on three benchmark hyperspectral datasets reveal that the proposed pipeline significantly increases the classification accuracy and generalization performance. To further validate the performance, several statistical tests are also considered such as Precision, Recall and F1-Score.
31 July 2025 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Hyperspectral image (HSI) classification presents inherent challenges due to high spectral dimensionality, significant domain shifts, and limited availability of labeled data. To address these issues, we propose a novel Active Transfer Learning (ATL) framework built upon a Spatial-Spectral Transformer (SST) backbone. The framework integrates multistage transfer learning with an uncertainty-diversity-driven active learning mechanism that strategically selects highly informative and diverse samples for annotation, thereby significantly reducing labeling costs and mitigating sample redundancy. A dynamic layer freezing strategy is introduced to enhance transferability and computational efficiency, enabling selective adaptation of model layers based on domain shift characteristics. Furthermore, we incorporate a self-calibrated attention mechanism that dynamically refines spatial and spectral weights during adaptation, guided by uncertainty-aware feedback. A diversity-promoting sampling strategy ensures broad spectral coverage among selected samples, preventing overfitting to specific classes. Extensive experiments on benchmark cross-domain HSI datasets demonstrate that the proposed SST-ATL framework achieves superior classification performance compared to conventional approaches. The source code is publicly available at https://github.com/mahmad000/ATL-SST.
Kleptography is the study of pilfering secure data secretly and subliminally. The concept of inserting backdoors was introduced two decades ago by Young and Yung. However, still it is a serious threat for modern cryptography. Different studies have proved that exploiting implementation errors of cryptographic algorithms needs less effort as compared to attacking its mathematical structure. Inserting the backdoor modifies the standard method of generating public and private key pairs in such away that the public information is meaningful for the attacker. This paper presents the kleptographic attack on cryptographic algorithm based on Elliptic curves. We show the technique of implementing backdoor against Edwards-curve Digital Signature Algorithm, Elliptic curve Diffie-Hellman key exchange scheme, Elliptic curve Digital Signature Algorithm, Elliptic curve Integrated Encryption Scheme, Elliptic curve ElGamal Encryption and Elliptic curve Qu-Vanstone implicit certificate scheme. In practical approach, backdoors are inserted in such a way that their identification is impossible by analyzing the output of an algorithm. Detection of kleptographic implementation is a complex task and very few studies can be found in this direction. We have explored the possibility of detection of malicious code inside the Elliptic curve based algorithms by using the idea of running time analysis. We have shown that by implementing strong Secretly Embedded Trapdoor with Universal Protection (SETUP) attack against Elliptic curve based algorithms, one can detect the presence of backdoor by analyzing the time difference in execution of an honest vs malicious version of code. We also modified the backdoor insertion mechanism in Edwards-curve Digital Signature Algorithm that results in negligible time difference making it impossible for the user to detect backdoor presence.
27 September 2024 in Neural Computing and Applications