Abstract Boomerang attack serves as a potent cryptanalytic tool for assessing the security of block ciphers. Over the past few years, various automatic search models for boomerang distinguishers have been proposed for block ciphers with different structures. This paper presents improved Mixed-Integer Linear Programming (MILP)-based search models for both single-key and related-key boomerang distinguishers. In the single-key scenario, we propose a method for dynamic allocation of active S-boxes. Our search model for single-key boomerang distinguishers characterizes the distinguisher probability more accurately, addressing the suboptimality issue caused by non-fixed weight assignments in prior models. In the related-key scenario, a search model for related-key boomerang distinguisher is proposed for block ciphers with bit-level key schedule algorithms, where the probability of the boomerang switch is ensured to be 1. To validate the effectiveness of our models, we apply them to the lightweight block cipher LILLIPUT based on Extended Generalized Feistel Networks (EGFN), conducting a comprehensive security analysis against boomerang attacks. Using our models, we successfully derive single-key boomerang distinguishers for 8 to 13 rounds and a 15-round related-key boomerang distinguisher. Notably, the data complexity required for 13-round single-key distinguishing attack is reduced by $${2^{ 3.172}}$$ 2 3.172 , and the 15-round related-key boomerang distinguisher with a probability of $${2^{ - 58}}$$ 2 - 58 is currently the longest-round distinguisher among all known distinguishers for LILLIPUT. The application results fully demonstrate the capability of our models in evaluating the security of block ciphers. This research not only provides new insights and methods for the design and analysis of lightweight block ciphers, but also deepens the understanding of the security characteristics for LILLIPUT.

Facial Expression Recognition (FER) poses significant challenges due to various imaging conditions, including diverse head poses, lighting conditions, resolutions, and occlusions. Additionally, different personal attributes such as age, gender, and racial background further contribute to the complexity of FER. To accurately extract meaningful expression features amidst these interfering factors to enhance recognition accuracy and the model’s generalization, we propose a Self Decoupling-Reconstruction Network (SDRNet). Specifically, our approach involves two learning processes. In the first phase, the network is trained to decouple facial images with expressions into expression and neutral components. This process involves reconstructing neutral facial images and the original input, ensuring the preservation of meaningful expression components devoid of interference in the decoupling process. In the second learning phase, we employ simple convolutional neural networks (CNNs) to recognize the extracted expression components. Our method has achieved state-of-the-art results across multiple widely used datasets, providing substantial evidence of its effectiveness. Additionally, we demonstrate the robust generalization performance of our approach through cross-database evaluations.

Predicting future motions of nearby agents is essential for an autonomous vehicle to take safe and effective actions. In this paper, we propose TSGN, a framework using Temporal Scene Graph Neural Networks with projected vectorized representations for multi-agent trajectory prediction. Projected vectorized representation models the traffic scene as a graph which is constructed by a set of vectors. These vectors represent agents, road network, and their spatial relative relationships. All relative features under this representation are both translation-and rotation-invariant. Based on this representation, TSGN captures the spatial-temporal features across agents, road network, interactions among them, and temporal dependencies of temporal traffic scenes. TSGN can predict multimodal future trajectories for all agents simultaneously, plausibly, and accurately. Mean-while, we propose a Hierarchical Lane Transformer for capturing interactions between agents and road network, which filters the surrounding road network and only keeps the most probable lane segments which could have an impact on the future behavior of the target agent. Without sacrificing the prediction performance, this greatly reduces the computational burden. Experiments show TSGN achieves state-of-the-art performance on the Argoverse motion forecasting benchmark.

High-quality corpora have been very scarce for the text emotion research. Existing corpora with multi-label emotion annotations have been either too small or too class-biased to properly support a supervised emotion learning. In this article, we propose a novel active learning method for efficiently instructing the human annotations for a less-biased and high-quality multi-label emotion corpus. Specifically, to compensate annotation for the minority-class examples, we propose a complementary sampling strategy based on unlabeled resources by measuring a probabilistic distance between the expected emotion label distribution in a temporary corpus and an uniform distribution. Qualitative evaluations are also given to the unlabeled examples, in which we evaluate the model uncertainties for multi-label emotion predictions, their syntactic representativeness for the other unlabeled examples, and their diverseness to the labeled examples, for a high-quality sampling. Through active learning, a supervised emotion classifier gets progressively improved by learning from these new examples. Experiment results suggest that by following these sampling strategies we can develop a corpus of high-quality examples with significantly relieved bias for emotion classes. Compared to the learning procedures based on traditional active learning algorithms, our learning procedure indicates the most efficient learning curve and estimates the best multi-label emotion predictions.

Understanding search engine users' intents has been a popular study in information retrieval, which directly affects the quality of retrieved information. One of the fundamental problems in this field is to find a connection between the entity in a query and the potential intents of the users, the latter of which would further reveal important information for facilitating the users' future actions. In this article, we present a novel research method for mining the actionable intents for search users, by generating a ranked list of the potentially most informative actions based on a massive pool of action samples. We compare different search strategies and their combinations for retrieving the action pool and develop three criteria for measuring the informativeness of the selected action samples, that is, the significance of an action sample within the pool, the representativeness of an action sample for the other candidate samples, and the diverseness of an action sample with respect to the selected actions. Our experiment, based on the Action Mining (AM) query entity data set from the Actionable Knowledge Graph (AKG) task at NTCIR‐13, suggests that the proposed approach is effective in generating an informative and early‐satisfying ranking of potential actions for search users.