Auditing recommendation systems has attracted growing attention due to increasing concerns over filter bubbles, unfairness, and data misuse. A common approach is sock-puppet auditing, where autonomous agents interact with platforms to reveal risks. However, existing approaches rely on hard-coded agents, lacking adaptability to dynamic GUI layouts and generating behaviors far from those of real users, limiting the comprehensiveness and representativeness of assessment. To address these issues, we introduce AuditAgent, an LLM-powered GUI-agent framework for risk auditing. AuditAgent simulates realistic user preferences and performs adaptive, human-like interactions on recommendation platforms. This design enables more thorough and faithful auditing, providing comprehensive assessments across multiple risk dimensions, including filter bubbles, unfairness, and data misuse.

Orthogonal time frequency space (OTFS) modulation has emerged as a promising solution for next-generation wireless systems, addressing the challenges of high Doppler effects and severe delay spread in complex communication scenarios. By integrating multiple input multiple output (MIMO) technology with OTFS, spectral efficiency is substantially enhanced through simultaneous multi stream transmission over identical spectral resources, while maintaining transmission reliability without bandwidth expansion. In this paper, we propose a new scheme called the MIMO-OTFS system based on three-dimensional constellation diagrams (3D-MIMO-OTFS), which improves the minimum Euclidean distance (MED) of the system through three-dimensional constellation diagrams and enhances the spectrum efficiency of the system through MIMO technology. According to the simulation results, the bit error rate performance and spectrum efficiency of the proposed system are superior to those of the reference system.

As a novel wireless transmission scheme, multi-mode orthogonal frequency division multiplexing with index modulation (MM-OFDM-IM) is proposed recently, where multiple distinguishable constellations (modes) and their full permutation are employed for data transmission. However, the minimum intra-mode distance (MIAD) and inter-mode distance (MIRD) of the two dimensional (2D) multi-mode constellation decrease significantly as the constellation size becomes larger, degrading the error performance of the system. To meet this challenge, we propose a new modulation technique called high-dimensional MM-OFDM-IM (HM-OFDM-IM), where the high dimensional (HD) multi-mode constellations with considerably larger MIAD and MIRD are utilized. Besides, since index bits which consumes no energy accounts for larger proportion, the proposed scheme achieves higher energy efficiency (EE). However, HM-OFDM-IM can not provide any diversity gain, which is critical for the ultra-reliable communication in the fading channel. Therefore, the fading-resistant HM-OFDM-IM (RF-HM-OFDM-IM) is also proposed by introducing the rotated signal constellation, where the diversity order of symbol bits is identical with the dimension of the constellation. By minimizing the maximum pairwise error probability (PEP), the optimal rotation angles are obtained. Finally, the proposed schemes, as revealed by the theoretical analyses and simulation results, provide the better error performance compared with state-of-the-art IM-based schemes in the Rayleigh fading channel.

Anomaly detection is a useful technique in many applications such as network security and fraud detection. Due to the insufficiency of anomaly samples as training data, it is usually formulated as an unsupervised model learning problem. In recent years there is a surge of adopting graph data structure in numerous applications. Detecting anomaly in an attributed network is more challenging than the sample based task because of the sample information representations in the form of graph nodes and edges. In this paper, we propose a generative adversarial attributed network (GAAN) anomaly detection framework. The fake graph nodes are generated by a generator module with Gaussian noise as input. An encoder module is employed to map both real and fake graph nodes into a latent space. To encode the graph structure information into the node latent representation, we compute the sample covariance matrix for real nodes and fake nodes respectively. A discriminator is trained to recognize whether two connected nodes are from the real or fake graph. With the learned encoder module output, an anomaly evaluation measurement considering the sample reconstruction error and real-sample identification confidence is employed to make prediction. We conduct extensive experiments on benchmark datasets and compare with state-of-the-art attributed graph anomaly detection methods. The superior AUC score demonstrates the effectiveness of the proposed method.

Two three‐dimensional (3D) 16‐ary signal constellations having extended lattice structures are presented in this paper. The theoretical symbol error probabilities (SEPs) of the new constellations in additive white Gaussian noise (AWGN) and Rayleigh fading channel are derived. Computer simulation confirms that the closed‐form expressions for average SEPs of the constellations in the AWGN channel are very accurate. The theoretical SEP upper bounds in the Rayleigh fading channel are very tight. Since the presented constellations have larger minimum Euclidean distance (MED) than the conventional one, error performance can be improved up to 0.9 dB in an AWGN environment. Hence, the proposed constellations and their theoretical analysis can be used as a reference for the development of a wireless communication system with 3D signal constellations.

The search range (SR) parameter plays an important role in motion estimation (ME) for video coding. Adaptively adjusting SR according to the information given by previously encoded syntax element, also known as adaptive search range (ASR) algorithm, can efficiently reduce the computational complexity of ME. Compared with heuristic search pattern (HSP) algorithms like diamond/hexagon search, ASR algorithms are more fundamental, flexible and hardware-oriented. This paper although starts with a comparison between HSP and ASP algorithms which is followed by a proposed ASR algorithm with experimental results, however more likely intends to contribute several novel perspectives to this research area.