Ji Won Yoon

Unknown custom protocols in space communication often complicate security analysis. A key challenge in protocol reverse engineering (PRE) is identifying the original protocol that a new variant is based on—a critical step that is often manual and time‐consuming. This paper presents SpaceProtoNet , a novel framework that employs a convolutional neural network (CNN) to classify protocol types from image representations of raw packet data. Experimental results demonstrate that SpaceProtoNet effectively generalises from known protocols to classify unseen variants into their correct base families, showing an F1‐score of 0.96 even when only four packets are available. The framework also maintains robustness in adverse conditions, sustaining an F1‐score of 0.91 even with a 10% bit error rate (BER). By automating this crucial identification step, SpaceProtoNet provides a systematic foundation for PRE, where the predicted base protocol family can help narrow the analysis scope and reduce the complexity of security analysis for space communication systems.

Homomorphic encryption (HE) is a critical tool for ensuring privacy and security in computing on sensitive data within untrusted environments. While HE offers advantages in non-interactive secure computation, it has not yet become practical for data analysis involving costly matrix operations in high-dimensional spaces. In this paper, we present an innovative approach to accelerating the extraction procedure in the permutation of matrices in vector representation, specifically addressing the challenges posed by SIMD structures within BGV-like schemes. Our work significantly accelerates matrix operations, as these operations inherently involve the permutation of matrices in the HE setting. For the extraction operation, we achieved a time complexity of O ( kN + k ² ), a notable improvement over the traditional O ( N log N ), making our method particularly beneficial in scenarios with large disparities between the polynomial degree N and the number of extracting elements k . In our experiments, the proposed extraction method showed up to 7.55× efficiency improvement, and for matrix multiplication, we achieved up to 2.39× improvement over the classical method.

Many automatic speech recognition (ASR) systems provide functions such as sending messages or opening garage doors. If such a system malfunctions, it could pose a significant threat. In this paper, we propose the attack scenario in which we transfer audio adversarial examples to radio system through the radio signal and the sound received through radio deceives the ASR system. In addition, we propose over-the-air technology using environmental noise so that we can attack easily and effectively. Using this method, we observed that the combined sound was much more robust to environmental noise than the non-combined sound. Finally, we experiment as our scenario on a real environment with adversarial examples created using environmental noise and show the results. Our attack succeeded against commercial ASR systems with a success rate of over 50%.

Unmanned Aerial Vehicles (UAVs) are aerial vehicles that can go to a particular position without human control or with remote human control. It is because unmanned control mainly relies on position estimation that a lot of research has been studied on GPS spoofing attacks. Detection methods against GPS spoofing attacks mainly include monitoring RF signals or IMU sensor values inside UAVs. In this work, we analyze GPS attack and detection in an advanced autopilot system, PX4 without excluding RF detection. Recent studies have shown that GPS spoofing is unable to evade the detection using EKF sensor fusion. Therefore, this paper experiment whether the detection could be evaded by strengthening the attacker model. This paper classifies attacker models according to whether an attacker knows the true position of UAVs or the estimated position by UAV and proposed attack methods depending on each model in PX4. We inject GPS value which our attack method intends to UAV during mission flight in simulation environment. By manipulating the GPS driver code of PX4 controller, we inject GPS value the attack method wants into UAV in physical environment. Finally, we observed the innovation test ratio during GPS spoofing and demonstrate that GPS spoofing attack is possible keeping the innovation test ratio under the anomaly detection criterion. After that, we proposed our approach which scales the EKF’s Kalman gain randomly to increase the detection method’s efficiency and experiment with the attack methods. This detection method has little effect on the test ratio without the attack. But during the attack, the innovation test ratio was increased higher than the anomaly detection criterion so that the attack could be detected.