arXiv subjects
Publications and source records attributed to Yuyang Zhou.
We derive a determinantal expression for the inhomogeneous asymmetric five vertex model in a rectangular geometry with arbitrary boundary conditions at the bottom and top. Standard non-intersecting lattice path, or free fermion, approaches are not applicable and the determinantal form thus is not immediate.
Machine learning (ML) has gained significant adoption in Android malware detection to address the escalating threats posed by the rapid proliferation of malware attacks. However, recent studies have revealed the inherent vulnerabilities of ML-based detection systems to evasion attacks. While efforts have been made to address this critical issue, many of the existing defensive methods encounter challenges such as lower effectiveness or reduced generalization capabilities. In this paper, we introduce MalPurifier, a novel adversarial purification framework specifically engineered for Android malware detection. Specifically, MalPurifier integrates three key innovations: a diversified adversarial perturbation mechanism for robustness and generalizability, a protective noise injection strategy for benign data integrity, and a Denoising AutoEncoder (DAE) with a dual-objective loss for accurate purification and classification. Extensive experiments on two large-scale datasets demonstrate that MalPurifier significantly outperforms state-of-the-art defenses. It robustly defends against a comprehensive set of 37 perturbation-based evasion attacks, consistently achieving robust accuracies above 90.91%. As a lightweight, model-agnostic, and plug-and-play module, MalPurifier offers a practical and effective solution to bolster the security of ML-based Android malware detectors.
Supervised talking head forgery detection faces severe generalization challenges due to the continuous evolution of generators. By reducing reliance on generator-specific forgery patterns, self-supervised detectors offer stronger cross-generator robustness. However, existing research has mainly focused on building stronger detectors, while the discriminative capacity of trained detectors remains insufficiently exploited. In particular, for score-based self-supervised detectors, the limited discriminative ability on hard cases is often reflected in unreliable anomaly ordering, leaving room for further refinement. Motivated by this observation, we draw inspiration from the dual-system theory of human cognition and propose a Training-Free Dual-System (TFDS) framework to further exploit the latent discriminative capacity of existing score-based self-supervised detectors. TFDS treats anomaly-like scores as the basis of System-1, using lightweight threshold-based routing to partition samples into confident and uncertain subsets. System-2 then revisits only the uncertain subset, performing fine-grained evidence-guided reasoning to refine the relative ordering of ambiguous samples within the original score distribution. Extensive experiments demonstrate consistent improvements across datasets and perturbation settings, with the gains arising mainly from corrected ordering within the uncertain subset. These findings show that existing self-supervised talking head forgery detectors still contain underexploited discriminative cues that can be effectively unlocked through training-free dual-system reasoning.
Video Temporal Grounding (VTG) faces a cross-modal semantic gap that often leads to background features being incorrectly aligned with the query, while directly matching the query to moments results in insufficient discriminability and consistency of temporal semantics. To address this issue, we propose MLLM-Assisted Semantic-Relational Consistent Alignment (MASRA), a training-time MLLM-based optimization framework for VTG. MASRA leverages an MLLM during training to produce two forms of textual priors, namely event-level descriptions with temporal spans and clip-level captions, and instantiates two MLLM-assisted alignments. Event Semantic Temporal Alignment (ESTA) aligns temporal context with event semantics to explicitly strengthen the correspondence between semantics and temporal events and improve span-level separability. Local Relational Consistency Alignment (LRCA) constructs a textual relation matrix derived from clip-level captions and aligns it with the temporal feature similarity matrix in the model, enhancing temporal consistency while capturing local structural information. MASRA includes two simple supporting modules, semantic-guided enhancement and second-order relational attention, to better utilize the learned semantic context and relational structure. Moreover, we introduce Decoupled Alignment Interaction (DAI) with a context-aware codebook to adaptively absorb query-irrelevant semantics and alleviate the cross-modal gap. The MLLM is only invoked during training and is not used at inference. Extensive experiments show that MASRA outperforms existing methods, and ablation studies validate its effectiveness.
The rapid evolution of generative models has enabled the creation of highly realistic and diverse synthetic images, posing significant challenges to reliable and generalizable Synthetic Image Detection (SID). However, existing detectors are typically trained on limited and biased datasets, resulting in poor generalization to unseen generators. To address this issue, we propose HiMix, a unified framework that enhances generalization by expanding the training distribution and promoting artifact-aware representations. Specifically, the Mixup-driven Distributional Augmentation (MDA) module constructs continuous transitional samples between real and fake images, improving coverage of low-confidence regions and exposing the model to more challenging samples, while the pixel-wise mixup operation smoothly perturbs semantics to enhance sensitivity to low-level artifacts. Moreover, the Hierarchical Artifact-aware Representation (HAR) module aggregates artifact information from both global and local levels through cross-layer integration and coarse-to-fine feature fusion, enabling the extraction of discriminative forgery representations under diverse distributions. Extensive experiments across multiple benchmarks demonstrate that HiMix achieves state-of-the-art performance, establishing well-separated logits for improved generalization to unseen forgeries.
We present a search for polarization oscillation of the Crab Nebula, also known as Tau A, at millimeter wavelengths using observations with the Simons Array, the successor experiment to POLARBEAR. We follow up on previous work by POLARBEAR using 90 GHz band data of the 2023 observing season of the Simons Array to evaluate the variability of Tau A's polarization angle. Tau A is widely used as a polarization angle calibration source in millimeter-wave astronomy, and thus it is necessary to validate the stability. Additionally, an interesting application of the time-resolved polarimetry of Tau A is to search for axion-like particles (ALPs). We do not detect a global signal across the frequencies considered in this analysis and place a median 95% upper bound of polarization oscillation amplitude $A<0.12^{\circ}$ over oscillation frequencies from 3.39 year$^{-1}$ to 1.50 day$^{-1}$. This constrains the ALP-photon coupling at a median 95% upper bound of $g_{aγγ}< 3.84\times 10^{-12}\times\left(m_a/10^{-21}\,\mathrm{eV}\right)$ in the mass range from $4.4\times10^{-22}$ to $7.2\times10^{-20}$ eV, assuming the ALP constitutes all of dark matter, its field is a stochastic Gaussian field, and it is the sole source of Tau A's polarization angle oscillation. Additionally, we do not detect signal at the frequencies where 2.5$σ$ hints were previously reported by POLARBEAR, but we do not exclude these signals at the 95% confidence level.
The rapid evolution of cloud computing technologies and the increasing number of cloud applications have provided numerous benefits in our daily lives. However, the diversity and complexity of different components pose a significant challenge to cloud security, especially when dealing with sophisticated and advanced cyberattacks such as Denial of Service (DoS). Recent advancements in the large language models (LLMs) offer promising solutions for security intelligence. By exploiting the powerful capabilities in language understanding, data analysis, task inference, action planning, and code generation, we present LLM-PD, a novel defense architecture that proactively mitigates various DoS threats in cloud networks. LLM-PD can efficiently make decisions through comprehensive data analysis and sequential reasoning, as well as dynamically create and deploy actionable defense mechanisms. Furthermore, it can flexibly self-evolve based on experience learned from previous interactions and adapt to new attack scenarios without additional training. Our case study on three distinct DoS attacks demonstrates its remarkable ability in terms of defense effectiveness and efficiency when compared with other existing methods.
The proliferation of UAVs has enabled a wide range of mission-critical applications and is becoming a cornerstone of low-altitude networks, supporting smart cities, emergency response, and more. However, the open wireless environment, dynamic topology, and resource constraints of UAVs expose low-altitude networks to severe DoS threats. Traditional defense approaches, which rely on fixed configurations or centralized decision-making, cannot effectively respond to the rapidly changing conditions in UAV swarm environments. To address these challenges, we propose a novel federated multi-agent deep reinforcement learning (FMADRL)-driven moving target defense (MTD) framework for proactive DoS mitigation in low-altitude networks. Specifically, we design lightweight and coordinated MTD mechanisms, including leader switching, route mutation, and frequency hopping, to disrupt attacker efforts and enhance network resilience. The defense problem is formulated as a multi-agent partially observable Markov decision process, capturing the uncertain nature of UAV swarms under attack. Each UAV is equipped with a policy agent that autonomously selects MTD actions based on partial observations and local experiences. By employing a policy gradient-based algorithm, UAVs collaboratively optimize their policies via reward-weighted aggregation. Extensive simulations demonstrate that our approach significantly outperforms state-of-the-art baselines, achieving up to a 34.6% improvement in attack mitigation rate, a reduction in average recovery time of up to 94.6%, and decreases in energy consumption and defense cost by as much as 29.3% and 98.3%, respectively, under various DoS attack strategies. These results highlight the potential of intelligent, distributed defense mechanisms to protect low-altitude networks, paving the way for reliable and scalable low-altitude economy.
With the continuous development of network environments and technologies, ensuring cyber security and governance is increasingly challenging. Network traffic classification(ETC) can analyzes attributes such as application categories and malicious intent, supporting network management services like QoS optimization, intrusion detection, and targeted billing. As the prevalence of traffic encryption increases, deep learning models are relied upon for content-agnostic analysis of packet sequences. However, the emergence of new services and attack variants often leads to incremental tasks for ETC models. To ensure model effectiveness, incremental learning techniques are essential; however, recent studies indicate that neural networks experience declining plasticity as tasks increase. We identified plasticity issues in existing incremental learning methods across diverse traffic samples and proposed the PRIME framework. By observing the effective rank of model parameters and the proportion of inactive neurons, the PRIME architecture can appropriately increase the parameter scale when the model's plasticity deteriorates. Experiments show that in multiple encrypted traffic datasets and different category increment scenarios, the PRIME architecture performs significantly better than other incremental learning algorithms with minimal increase in parameter scale.
Modern neural architecture search (NAS) is inherently multi-objective, balancing trade-offs such as accuracy, parameter count, and computational cost. This complexity makes NAS computationally expensive and nearly impossible to solve without efficient approximations. To address this, we propose a novel surrogate modelling approach that leverages an ensemble of Siamese network blocks to predict dominance relationships between candidate architectures. Lightweight and easy to train, the surrogate achieves 92% accuracy and replaces the crowding distance calculation in the survivor selection strategy with a heuristic rule based on model size. Integrated into a framework termed SiamNAS, this design eliminates costly evaluations during the search process. Experiments on NAS-Bench-201 demonstrate the framework's ability to identify Pareto-optimal solutions with significantly reduced computational costs. The proposed SiamNAS identified a final non-dominated set containing the best architecture in NAS-Bench-201 for CIFAR-10 and the second-best for ImageNet, in terms of test error rate, within 0.01 GPU days. This proof-of-concept study highlights the potential of the proposed Siamese network surrogate model to generalise to multi-tasking optimisation, enabling simultaneous optimisation across tasks. Additionally, it offers opportunities to extend the approach for generating Sets of Pareto Sets (SOS), providing diverse Pareto-optimal solutions for heterogeneous task settings.
Prompt tuning has become a popular strategy for adapting Vision-Language Models (VLMs) to zero/few-shot visual recognition tasks. Some prompting techniques introduce prior knowledge due to its richness, but when learnable tokens are randomly initialized and disconnected from prior knowledge, they tend to overfit on seen classes and struggle with domain shifts for unseen ones. To address this issue, we propose the InPK model, which infuses class-specific prior knowledge into the learnable tokens during initialization, thus enabling the model to explicitly focus on class-relevant information. Furthermore, to mitigate the weakening of class information by multi-layer encoders, we continuously reinforce the interaction between learnable tokens and prior knowledge across multiple feature levels. This progressive interaction allows the learnable tokens to better capture the fine-grained differences and universal visual concepts within prior knowledge, enabling the model to extract more discriminative and generalized text features. Even for unseen classes, the learned interaction allows the model to capture their common representations and infer their appropriate positions within the existing semantic structure. Moreover, we introduce a learnable text-to-vision projection layer to accommodate the text adjustments, ensuring better alignment of visual-text semantics. Extensive experiments on 11 recognition datasets show that InPK significantly outperforms state-of-the-art methods in multiple zero/few-shot image classification tasks.
The rapid advancement of internet technology has led to a surge in data transmission, making network traffic classification crucial for security and management. However, there are significant deficiencies in its efficiency for handling multiattribute analysis and its ability to expand model knowledge, making it difficult to adapt to the ever-changing network environment and complex identification requirements. To address this issue, we proposed the SNAKE (Sustainable Network Analysis with Knowledge Exploration) system, which adopts a multi-gated mixture of experts architecture to construct a multi-functional traffic classification model. The system analyzes traffic attributes at different levels through multiple expert sub-models, providing predictions for these attributes via gating and a final Tower network. Additionally, through an intelligent gating configuration, the system enables extremely fast model integration and evolution across various knowledge expansion scenarios. Its excellent compatibility allows it to continuously evolve into a multi-functional largescale model in the field of traffic analysis. Our experimental results demonstrate that the SNAKE system exhibits remarkable scalability when faced with incremental challenges in diverse traffic classification tasks. Currently, we have integrated multiple models into the system, enabling it to classify a wide range of attributes, such as encapsulation usage, application types and numerous malicious behaviors. We believe that SNAKE can pioneeringly create a sustainable and multifunctional large-scale model in the field of network traffic analysis after continuous expansion.
E to B mixing or "leakage" due to time-ordered data (TOD) filtering has become an important source of sensitivity loss that ground-based cosmic microwave background polarization experiments must address. However, it is a difficult problem for which very few viable solutions exist. In this paper, we expand upon satellite E-mode methods to cover E/B leakage specifically due to TOD filtering. We take a satellite E-mode map and TOD filter it through the ground-based experiment data analysis pipeline, from which we construct a map-space "leakage template" and subtract it from the ground-based experiment map. We evaluate the residual leakage by simulating the satellite E-mode maps with Planck-like and LiteBIRD-like noise levels, and simulate the ground-based experiment with Simons Observatory-like and CMB-S4-like noise levels. The effectiveness of the method is measured in the improvement of the Fisher uncertainty $σ(r=0)$. We find that our method can reduce $σ(r=0)$ by $\sim15\text{--}75\%$ depending on the noise levels considered.
Encrypted traffic classification technology is a crucial decision-making information source for network management and security protection. It has the advantages of excellent response timeliness, large-scale data bearing, and cross-time-and-space analysis. The existing research on encrypted traffic classification has gradually transitioned from the closed world to the open world, and many classifier optimization and feature engineering schemes have been proposed. However, encrypted traffic classification has yet to be effectively applied to the actual network environment. The main reason is that applications on the Internet are constantly updated, including function adjustment and version change, which brings severe feature concept drift, resulting in rapid failure of the classifier. Hence, the entire model must be retrained only past very fast time, with unacceptable labeled sample constructing and model training cost. To solve this problem, we deeply study the characteristics of Internet application updates, associate them with feature concept drift, and then propose self-evolving encrypted traffic classification. We propose a feature concept drift determination method and a drift-oriented self-evolving fine-tuning method based on the Laida criterion to adapt to all applications that are likely to be updated. In the case of no exact label samples, the classifier evolves through fully fine-tuning continuously, and the time interval between two necessary retraining is greatly extended to be applied to the actual network environment. Experiments show that our approach significantly improves the classification performance of the original classifier on the following stage dataset of the following months (9\% improvement on F1-score) without any hard-to-acquire labeled sample. Under the current experimental environment, the life of the classifier is extended to more than eight months.
The ray-tracing is often employed in urban areas for channel modeling with high accuracy but encounters a substantial computational complexity for high mobility scenarios. In this paper, we propose a novel pre-processing method for dynamic ray-tracing to reduce the computational burden in high-mobility scenarios by prepending the intersection judgment to the pre-processing stage. The proposed method generates an inter-visibility matrix that establishes visibility relationships among static objects in the environment considering the intersection judgment. Moreover, the inter-visibility matrix can be employed to create the inter-visibility table for mobile transmitters and receivers, which can improve the efficiency of constructing an image tree for the three-dimensional (3D) dynamic ray-tracing method. The results show that the proposed pre-processing method in dynamic ray-tracing has considerable time-saving compared with the traditional method while maintaining the same accuracy. The channel characteristics computed by the proposed method can well match to the channel measurements.
Multimedia-based recommendation provides personalized item suggestions by learning the content preferences of users. With the proliferation of digital devices and APPs, a huge number of new items are created rapidly over time. How to quickly provide recommendations for new items at the inference time is challenging. What's worse, real-world items exhibit varying degrees of modality missing(e.g., many short videos are uploaded without text descriptions). Though many efforts have been devoted to multimedia-based recommendations, they either could not deal with new multimedia items or assumed the modality completeness in the modeling process. In this paper, we highlight the necessity of tackling the modality missing issue for new item recommendation. We argue that users' inherent content preference is stable and better kept invariant to arbitrary modality missing environments. Therefore, we approach this problem from a novel perspective of invariant learning. However, how to construct environments from finite user behavior training data to generalize any modality missing is challenging. To tackle this issue, we propose a novel Multimodality Invariant Learning reCommendation(a.k.a. MILK) framework. Specifically, MILK first designs a cross-modality alignment module to keep semantic consistency from pretrained multimedia item features. After that, MILK designs multi-modal heterogeneous environments with cyclic mixup to augment training data, in order to mimic any modality missing for invariant user preference learning. Extensive experiments on three real datasets verify the superiority of our proposed framework. The code is available at https://github.com/HaoyueBai98/MILK.
In this work, we present MoConVQ, a novel unified framework for physics-based motion control leveraging scalable discrete representations. Building upon vector quantized variational autoencoders (VQ-VAE) and model-based reinforcement learning, our approach effectively learns motion embeddings from a large, unstructured dataset spanning tens of hours of motion examples. The resultant motion representation not only captures diverse motion skills but also offers a robust and intuitive interface for various applications. We demonstrate the versatility of MoConVQ through several applications: universal tracking control from various motion sources, interactive character control with latent motion representations using supervised learning, physics-based motion generation from natural language descriptions using the GPT framework, and, most interestingly, seamless integration with large language models (LLMs) with in-context learning to tackle complex and abstract tasks.
This paper characterizes the proximal operator of the piece-wise exponential function $1\!-\!e^{-|x|/σ}$ with a given shape parameter $σ\!>\!0$, which is a popular nonconvex surrogate of $\ell_0$-norm in support vector machines, zero-one programming problems, and compressed sensing, etc. Although Malek-Mohammadi et al. [IEEE Transactions on Signal Processing, 64(21):5657--5671, 2016] once worked on this problem, the expressions they derived were regrettably inaccurate. In a sense, it was lacking a case. Using the Lambert W function and an extensive study of the piece-wise exponential function, we have rectified the formulation of the proximal operator of the piece-wise exponential function in light of their work. We have also undertaken a thorough analysis of this operator. Finally, as an application in compressed sensing, an iterative shrinkage and thresholding algorithm (ISTA) for the piece-wise exponential function regularization problem is developed and fully investigated. A comparative study of ISTA with nine popular non-convex penalties in compressed sensing demonstrates the advantage of the piece-wise exponential penalty.