Arboreal environments challenge current robots but are deftly traversed by many familiar animals such as squirrels. We present a small, 450 g robot “Pinto” developed for tree-jumping, a behavior seen in squirrels but rarely in legged robots: jumping from the ground onto a vertical tree trunk. We develop a powerful and lightweight latched series-elastic actuator using a twisted string and carbon fiber springs. We consider the effects of scaling down conventional quadrupeds and experimentally show how storing energy in a parallel-elastic fashion using a latch increases jump energy compared to series-elastic or springless strategies. By switching between series and parallel-elastic modes with our latched 5-bar leg mechanism, Pinto executes energetic jumps as well as maintains continuous control during shorter bounding motions. We also develop sprung 2-DoF arms equipped with spined grippers to grasp tree bark for high-speed perching following a jump.

Ransomware poses a significant and constantly evolving threat that traditional static or dynamic analysis methods struggle to address independently due to challenges with evasion and scalability. This paper introduces MalFusion, a tightly-integrated, two-stage hybrid framework designed for robust and efficient ransomware detection. MalFusion first employs a lightweight static analysis module, which uses opcode sequences fed into a Random Forest to rapidly filter malicious files from benign ones. Files flagged as suspicious are then escalated to the dynamic analysis and hybrid classification module, which leverages a Multilayer Perceptron (MLP) to perform a fine-grained classification of ransomware versus other generic malware based on both opcode and API call sequences. The MLP classifier achieves a precision of 99.34%, highlighting the effectiveness of a hybrid approach to differentiate ransomware from other general malware. The source code is available at https://github.com/Leninadeee/MalFusion.