Staying on the Attack Path: Structured State for Long-Horizon Automated Penetration Testing
本文提出Intentest，通过意图图引导和持久化事实-意图DAG来解决长周期自动化渗透测试中上下文遗忘和意图漂移问题。
0 citationsRead paper
Selected work
Representative Papers
Calibrated Persistent-Laplacian CUSUM for Online Change-Point Detection
This work proposes a novel method for online change-point detection in high-dimensional nonlinear time series by integrating persistent homology with Laplacian spectra to simultaneously control false alarms and reduce detection delay. The approach maps sliding windows of the time series into point clouds and leverages persistent Laplacian spectra—going beyond conventional homology-based counts—to capture scale-dependent geometric structures and connectivity. Embedded within a recursive Page-CUSUM monitoring framework, the method enables efficient real-time surveillance. By incorporating whitened scores and a two-phase (Phase I/II) parameter calibration procedure, it provides theoretical guarantees for false alarm control over finite monitoring horizons. Empirical evaluations on both synthetic and real-world datasets demonstrate consistently reliable false alarm rates and state-of-the-art detection performance.
0 citationsRead paper
Drug Synergy Prediction via Residual Graph Isomorphism Networks and Attention Mechanisms
Traditional monotherapy often suffers from limited efficacy and rapid development of drug resistance, while experimental screening of drug combinations is prohibitively expensive, necessitating efficient computational approaches to predict synergistic effects. This work proposes ResGIN-Att, a novel model that integrates drug molecular structures, cell line genomic profiles, and inter-drug interactions. It employs a residual graph isomorphism network to capture multi-scale topological features and mitigate over-smoothing, combines an adaptive LSTM to aggregate structural information from local to global levels, and introduces a cross-attention mechanism to explicitly model drug–drug interactions and identify critical substructures. Evaluated on five public datasets, the method significantly outperforms state-of-the-art baselines, demonstrating superior generalization and robustness.
0 citationsRead paper
Vision-Based Early Fault Diagnosis and Self-Recovery for Strawberry Harvesting Robots
This study addresses frequent harvesting failures in strawberry-picking robots caused by fragmented visual perception, misalignment between fruit and end-effector, empty grasps, and fruit slippage. To this end, the authors propose a fault diagnosis and self-recovery framework integrating multi-task visual perception with corrective control. They introduce SRR-Net, an end-to-end model that jointly performs strawberry detection, segmentation, and maturity estimation. Leveraging a micro-optical camera mounted on the gripper, the system incorporates a relative position error compensation mechanism between target and gripper, alongside a MobileNetV3-Small-based grasp state classifier and an LSTM-based slippage prediction module for early fault detection and real-time intervention. Experimental results demonstrate that SRR-Net achieves high performance in detection (precision: 0.895, recall: 0.813), segmentation (precision: 0.887, recall: 0.747), and maturity estimation (MAE: 0.035), with an inference speed of 163.35 FPS, significantly enhancing harvesting reliability and efficiency.
0 citationsRead paper
A Spatial Semantics and Continuity Perception Attention for Remote Sensing Water Body Change Detection
To address the challenges of data scarcity and inadequate modeling of spatial semantics and structural continuity in high-spatial-resolution remote sensing water body change detection (WBCD), this paper introduces HSRW-CD—the first WBCD benchmark dataset with spatial resolution superior to 3 meters—and proposes the Spatial-Semantic and Continuity-aware Attention (SSCP) module. SSCP jointly models water body spatial semantic priors and topological continuity by integrating Multi-Semantic Spatial Attention (MSA), Structural-Relation Guided Global Attention (SRGA), and Channel-wise Self-Attention (CSA). Designed as a plug-and-play component, SSCP significantly improves the performance of mainstream change detection models on both HSRW-CD and Water-CD, enhancing discriminability of water body features. Experimental results demonstrate its strong generalizability and cross-dataset transferability.
0 citationsRead paper
Recent publications
Latest Papers
Staying on the Attack Path: Structured State for Long-Horizon Automated Penetration Testing
本文提出Intentest，通过意图图引导和持久化事实-意图DAG来解决长周期自动化渗透测试中上下文遗忘和意图漂移问题。
0 citationsRead paper
Calibrated Persistent-Laplacian CUSUM for Online Change-Point Detection
This work proposes a novel method for online change-point detection in high-dimensional nonlinear time series by integrating persistent homology with Laplacian spectra to simultaneously control false alarms and reduce detection delay. The approach maps sliding windows of the time series into point clouds and leverages persistent Laplacian spectra—going beyond conventional homology-based counts—to capture scale-dependent geometric structures and connectivity. Embedded within a recursive Page-CUSUM monitoring framework, the method enables efficient real-time surveillance. By incorporating whitened scores and a two-phase (Phase I/II) parameter calibration procedure, it provides theoretical guarantees for false alarm control over finite monitoring horizons. Empirical evaluations on both synthetic and real-world datasets demonstrate consistently reliable false alarm rates and state-of-the-art detection performance.
0 citationsRead paper
Drug Synergy Prediction via Residual Graph Isomorphism Networks and Attention Mechanisms
Traditional monotherapy often suffers from limited efficacy and rapid development of drug resistance, while experimental screening of drug combinations is prohibitively expensive, necessitating efficient computational approaches to predict synergistic effects. This work proposes ResGIN-Att, a novel model that integrates drug molecular structures, cell line genomic profiles, and inter-drug interactions. It employs a residual graph isomorphism network to capture multi-scale topological features and mitigate over-smoothing, combines an adaptive LSTM to aggregate structural information from local to global levels, and introduces a cross-attention mechanism to explicitly model drug–drug interactions and identify critical substructures. Evaluated on five public datasets, the method significantly outperforms state-of-the-art baselines, demonstrating superior generalization and robustness.
0 citationsRead paper
Vision-Based Early Fault Diagnosis and Self-Recovery for Strawberry Harvesting Robots
This study addresses frequent harvesting failures in strawberry-picking robots caused by fragmented visual perception, misalignment between fruit and end-effector, empty grasps, and fruit slippage. To this end, the authors propose a fault diagnosis and self-recovery framework integrating multi-task visual perception with corrective control. They introduce SRR-Net, an end-to-end model that jointly performs strawberry detection, segmentation, and maturity estimation. Leveraging a micro-optical camera mounted on the gripper, the system incorporates a relative position error compensation mechanism between target and gripper, alongside a MobileNetV3-Small-based grasp state classifier and an LSTM-based slippage prediction module for early fault detection and real-time intervention. Experimental results demonstrate that SRR-Net achieves high performance in detection (precision: 0.895, recall: 0.813), segmentation (precision: 0.887, recall: 0.747), and maturity estimation (MAE: 0.035), with an inference speed of 163.35 FPS, significantly enhancing harvesting reliability and efficiency.
0 citationsRead paper
A Spatial Semantics and Continuity Perception Attention for Remote Sensing Water Body Change Detection
To address the challenges of data scarcity and inadequate modeling of spatial semantics and structural continuity in high-spatial-resolution remote sensing water body change detection (WBCD), this paper introduces HSRW-CD—the first WBCD benchmark dataset with spatial resolution superior to 3 meters—and proposes the Spatial-Semantic and Continuity-aware Attention (SSCP) module. SSCP jointly models water body spatial semantic priors and topological continuity by integrating Multi-Semantic Spatial Attention (MSA), Structural-Relation Guided Global Attention (SRGA), and Channel-wise Self-Attention (CSA). Designed as a plug-and-play component, SSCP significantly improves the performance of mainstream change detection models on both HSRW-CD and Water-CD, enhancing discriminability of water body features. Experimental results demonstrate its strong generalizability and cross-dataset transferability.
0 citationsRead paper