arXiv subjects

Shuhao Li

Publications and source records attributed to Shuhao Li.

At least 37 records · Page 2Linked to original sources

arXiv2025

ACORN: Adaptive Contrastive Optimization for Safe and Robust Fine-Grained Robotic Manipulation

Embodied AI research has traditionally emphasized performance metrics such as success rate and cumulative reward, overlooking critical robustness and safety considerations that emerge during real-world deployment. In actual environments, agents continuously encounter unpredicted situations and distribution shifts, causing seemingly reliable policies to experience catastrophic failures, particularly in manipulation tasks. To address this gap, we introduce four novel safety-centric metrics that quantify an agent's resilience to environmental perturbations. Building on these metrics, we present Adaptive Contrastive Optimization for Robust Manipulation (ACORN), a plug-and-play algorithm that enhances policy robustness without sacrificing performance. ACORN leverages contrastive learning to simultaneously align trajectories with expert demonstrations while diverging from potentially unsafe behaviors. Our approach efficiently generates informative negative samples through structured Gaussian noise injection, employing a double perturbation technique that maintains sample diversity while minimizing computational overhead. Comprehensive experiments across diverse manipulation environments validate ACORN's effectiveness, yielding improvements of up to 23% in safety metrics under disturbance compared to baseline methods. These findings underscore ACORN's significant potential for enabling reliable deployment of embodied agents in safety-critical real-world applications.

cs.RO↗

arXiv2025

LUK: Empowering Log Understanding with Expert Knowledge from Large Language Models

Logs play a critical role in providing essential information for system monitoring and troubleshooting. Recently, with the success of pre-trained language models (PLMs) and large language models (LLMs) in natural language processing (NLP), smaller PLMs (such as BERT) and LLMs (like GPT-4) have become the current mainstream approaches for log analysis. Despite the remarkable capabilities of LLMs, their higher cost and inefficient inference present significant challenges in leveraging the full potential of LLMs to analyze logs. In contrast, smaller PLMs can be fine-tuned for specific tasks even with limited computational resources, making them more practical. However, these smaller PLMs face challenges in understanding logs comprehensively due to their limited expert knowledge. To address the lack of expert knowledge and enhance log understanding for smaller PLMs, this paper introduces a novel and practical knowledge enhancement framework, called LUK, which acquires expert knowledge from LLMs automatically and then enhances the smaller PLM for log analysis with these expert knowledge. LUK can take full advantage of both types of models. Specifically, we design a multi-expert collaboration framework based on LLMs with different roles to acquire expert knowledge. In addition, we propose two novel pre-training tasks to enhance the log pre-training with expert knowledge. LUK achieves state-of-the-art results on different log analysis tasks and extensive experiments demonstrate expert knowledge from LLMs can be utilized more effectively to understand logs. Our source code and detailed experimental data are available at https://github.com/LeaperOvO/LUK.

cs.SE↗

arXiv2025

AdaptiveLog: An Adaptive Log Analysis Framework with the Collaboration of Large and Small Language Model

Automated log analysis is crucial to ensure high availability and reliability of complex systems. The advent of LLMs in NLP has ushered in a new era of language model-driven automated log analysis, garnering significant interest. Within this field, two primary paradigms based on language models for log analysis have become prominent. Small Language Models (SLMs) follow the pre-train and fine-tune paradigm, focusing on the specific log analysis task through fine-tuning on supervised datasets. On the other hand, LLMs following the in-context learning paradigm, analyze logs by providing a few examples in prompt contexts without updating parameters. Despite their respective strengths, we notice that SLMs are more cost-effective but less powerful, whereas LLMs with large parameters are highly powerful but expensive and inefficient. To trade-off between the performance and inference costs of both models in automated log analysis, this paper introduces an adaptive log analysis framework known as AdaptiveLog, which effectively reduces the costs associated with LLM while ensuring superior results. This framework collaborates an LLM and a small language model, strategically allocating the LLM to tackle complex logs while delegating simpler logs to the SLM. Specifically, to efficiently query the LLM, we propose an adaptive selection strategy based on the uncertainty estimation of the SLM, where the LLM is invoked only when the SLM is uncertain. In addition, to enhance the reasoning ability of the LLM in log analysis tasks, we propose a novel prompt strategy by retrieving similar error-prone cases as the reference, enabling the model to leverage past error experiences and learn solutions from these cases. Extensive experiments demonstrate that AdaptiveLog achieves state-of-the-art results across different tasks, elevating the overall accuracy of log analysis while maintaining cost efficiency.

cs.SE↗

arXiv2024

IceDiff: High Resolution and High-Quality Sea Ice Forecasting with Generative Diffusion Prior

Variation of Arctic sea ice has significant impacts on polar ecosystems, transporting routes, coastal communities, and global climate. Tracing the change of sea ice at a finer scale is paramount for both operational applications and scientific studies. Recent pan-Arctic sea ice forecasting methods that leverage advances in artificial intelligence has made promising progress over numerical models. However, forecasting sea ice at higher resolutions is still under-explored. To bridge the gap, we propose a two-staged deep learning framework, IceDiff, to forecast sea ice concentration at finer scales. IceDiff first leverages an independently trained vision transformer to generate coarse yet superior forecasting over previous methods at a regular 25km x 25km grid. This high-quality sea ice forecasting can be utilized as reliable guidance for the next stage. Subsequently, an unconditional diffusion model pre-trained on sea ice concentration maps is utilized for sampling down-scaled sea ice forecasting via a zero-shot guided sampling strategy and a patch-based method. For the first time, IceDiff demonstrates sea ice forecasting with the 6.25km x 6.25km resolution. IceDiff extends the boundary of existing sea ice forecasting models and more importantly, its capability to generate high-resolution sea ice concentration data is vital for pragmatic usages and research.

physics.ao-ph↗

arXiv2024

Allium Vegetables Intake and Digestive System Cancer Risk: A Study Based on Mendelian Randomization, Network Pharmacology and Molecular Docking

Background: Allium vegetables (garlic and onion) are one of the flavorings in people's daily diets. Observational studies suggest that intake of allium vegetables may be correlated with a lower incidence of digestive system cancers. However, the existence of a causal relationship is still controversial due to confounding factors and reverse causation. Therefore, we explored the causal relationship between intake of allium vegetables and digestive system cancers using Mendelian randomization approach. Methods: First, we performed Mendelian randomization analyses using inverse variance weighting (IVW), weighted median, and MR-Egger approaches, and demonstrated the reliability of the results in the sensitivity step. Second, Multivariable Mendelian randomization was applied to adjust for smoking and alcohol consumption. Third, we explored the molecular mechanisms behind the positive results through network pharmacology and molecular docking methods. Results: The study suggests that increased intake of garlic reduced gastric cancer risk. However, onion intake was not statistically associated with digestive system cancer. Conclusion: Garlic may have a protective effect against gastric cancer.

q-bio.GN↗

arXiv2023

Dynamically configured physics-informed neural network in topology optimization applications

Integration of machine learning (ML) into the topology optimization (TO) framework is attracting increasing attention, but data acquisition in data-driven models is prohibitive. Compared with popular ML methods, the physics-informed neural network (PINN) can avoid generating enormous amounts of data when solving forward problems and additionally provide better inference. To this end, a dynamically configured PINN-based topology optimization (DCPINN-TO) method is proposed. The DCPINN is composed of two subnetworks, namely the backbone neural network (NN) and the coefficient NN, where the coefficient NN has fewer trainable parameters. The designed architecture aims to dynamically configure trainable parameters; that is, an inexpensive NN is used to replace an expensive one at certain optimization cycles. Furthermore, an active sampling strategy is proposed to selectively sample collocations depending on the pseudo-densities at each optimization cycle. In this manner, the number of collocations will decrease with the optimization process but will hardly affect it. The Gaussian integral is used to calculate the strain energy of elements, which yields a byproduct of decoupling the mapping of the material at the collocations. Several examples with different resolutions validate the feasibility of the DCPINN-TO method, and multiload and multiconstraint problems are employed to illustrate its generalization. In addition, compared to finite element analysis-based TO (FEA-TO), the accuracy of the displacement prediction and optimization results indicate that the DCPINN-TO method is effective and efficient.

cs.LG↗

arXiv2023

Analysis and Detection against Network Attacks in the Overlapping Phenomenon of Behavior Attribute

The proliferation of network attacks poses a significant threat. Researchers propose datasets for network attacks to support research in related fields. Then, many attack detection methods based on these datasets are proposed. These detection methods, whether two-classification or multi-classification, belong to single-label learning, i.e., only one label is given to each sample. However, we discover that there is a noteworthy phenomenon of behavior attribute overlap between attacks, The presentation of this phenomenon in a dataset is that there are multiple samples with the same features but different labels. In this paper, we verify the phenomenon in well-known datasets(UNSW-NB15, CCCS-CIC-AndMal-2020) and re-label these data. In addition, detecting network attacks in a multi-label manner can obtain more information, providing support for tracing the attack source and building IDS. Therefore, we propose a multi-label detection model based on deep learning, MLD-Model, in which Wasserstein-Generative-Adversarial- Network-with-Gradient-Penalty (WGAN-GP) with improved loss performs data enhancement to alleviate the class imbalance problem, and Auto-Encoder (AE) performs classifier parameter pre-training. Experimental results demonstrate that MLD-Model can achieve excellent classification performance. It can achieve F1=80.06% in UNSW-NB15 and F1=83.63% in CCCS-CIC-AndMal-2020. Especially, MLD-Model is 5.99%-7.97% higher in F1 compared with the related single-label methods.

cs.CR↗

arXiv2023

Detecting unknown HTTP-based malicious communication behavior via generated adversarial flows and hierarchical traffic features

Malicious communication behavior is the network communication behavior generated by malware (bot-net, spyware, etc.) after victim devices are infected. Experienced adversaries often hide malicious information in HTTP traffic to evade detection. However, related detection methods have inadequate generalization ability because they are usually based on artificial feature engineering and outmoded datasets. In this paper, we propose an HTTP-based Malicious Communication traffic Detection Model (HMCD-Model) based on generated adversarial flows and hierarchical traffic features. HMCD-Model consists of two parts. The first is a generation algorithm based on WGAN-GP to generate HTTP-based malicious communication traffic for data enhancement. The second is a hybrid neural network based on CNN and LSTM to extract hierarchical spatial-temporal features of traffic. In addition, we collect and publish a dataset, HMCT-2020, which consists of large-scale malicious and benign traffic during three years (2018-2020). Taking the data in HMCT-2020(18) as the training set and the data in other datasets as the test set, the experimental results show that the HMCD-Model can effectively detect unknown HTTP-based malicious communication traffic. It can reach F1 = 98.66% in the dataset HMCT-2020(19-20), F1 = 90.69% in the public dataset CIC-IDS-2017, and F1 = 83.66% in the real traffic, which is 20+% higher than other representative methods on average. This validates that HMCD-Model has the ability to discover unknown HTTP-based malicious communication behavior.

cs.CR↗

arXiv2023

A method based on hierarchical spatiotemporal features for trojan traffic detection

Trojans are one of the most threatening network attacks currently. HTTP-based Trojan, in particular, accounts for a considerable proportion of them. Moreover, as the network environment becomes more complex, HTTP-based Trojan is more concealed than others. At present, many intrusion detection systems (IDSs) are increasingly difficult to effectively detect such Trojan traffic due to the inherent shortcomings of the methods used and the backwardness of training data. Classical anomaly detection and traditional machine learning-based (TML-based) anomaly detection are highly dependent on expert knowledge to extract features artificially, which is difficult to implement in HTTP-based Trojan traffic detection. Deep learning-based (DL-based) anomaly detection has been locally applied to IDSs, but it cannot be transplanted to HTTP-based Trojan traffic detection directly. To solve this problem, in this paper, we propose a neural network detection model (HSTF-Model) based on hierarchical spatiotemporal features of traffic. Meanwhile, we combine deep learning algorithms with expert knowledge through feature encoders and statistical characteristics to improve the self-learning ability of the model. Experiments indicate that F1 of HSTF-Model can reach 99.4% in real traffic. In addition, we present a dataset BTHT consisting of HTTP-based benign and Trojan traffic to facilitate related research in the field.

cs.NI↗

arXiv2023

A novel reduced basis method for adjoint sensitivity analysis of dynamic topology optimization

In gradient-based time domain topology optimization, design sensitivity analysis (DSA) of the dynamic response is essential, and requires high computational cost to directly differentiate, especially for high-order dynamic system. To address this issue, this study develops an efficient reduced basis method (RBM)-based discrete adjoint sensitivity analysis method, which on the one hand significantly improves the efficiency of sensitivity analysis and on the other hand avoids the consistency errors caused by the continuum method. In this algorithm, the basis functions of the adjoint problem are constructed in the offline phase based on the greedy-POD method, and a novel model-based estimation is developed to facilitate the acceleration of this process. Based on these basis functions, a fast and reasonably accurate model is then built by Galerkin projection for sensitivity analysis in each dynamic topology optimization iteration. Finally, the effectiveness of the error measures, the efficiency and the accuracy of the presented reduced-order method are verified by 2D and 3D dynamic structure studies.

math.NA↗

arXiv2023

A novel multi-stage concurrent topology optimization for variable-stiffness structures

The concurrent optimization of topology and fibre orientation is a promising approach to pursue higher strength and lighter weight of variable-stiffness structure. This study proposes a novel discrete-continuous scheme for the concurrent optimization. Considering the global convergence, Discrete Material Optimization (DMO) is firstly utilized to select a dominant angle for each element from several predefined candidate angles. However, it is still difficult to obtain excellent fibre angle convergence due to difficulty in selection of candidate materials for some elements. Therefore, the Sequential Binary-Phase Topology Optimization is proposed to guarantee the uniqueness of the element to candidate angle mapping. Moreover, to obtain better mechanical properties, Continuous Fibre Angle Optimization (CFAO) with spatial filter is introduced to optimize fibre continuity. Several classic numerical examples are used to verify the excellent performance of the proposed method in terms of fibre angle convergence and stable optimization ability.

math.GT↗

arXiv2023

An efficient online successive reanalysis method for dynamic topology optimization

In this study, an efficient reanalysis strategy for dynamic topology optimization is proposed. Compared with other related studies, an online successive dynamic reanalysis method and POD-based approximate dynamic displacement strategy are integrated. In dynamic reanalysis, the storage of the stiffness matrix decomposition can be avoided and the reduced basis vectors should be updated successively according to the structural status in each iteration. Therefore, the bottleneck of combined approximation method for large-scale dynamic topology optimization can be handled. Sequentially, the Proper Orthogonal Decomposition (POD) is employed to obtain the approximate dynamic displacement, in which the Proper Orthogonal Mode (POM) of the displacement field is employed to establish the approximated equivalent static loads of Equivalent Static Load (ESL) method. Compared with the exact equivalent static loads at all the time intervals, the number of equivalent static loads is significantly reduced. Finally, the 2D and 3D test results indicate that the proposed method has remarkable speed-up effect on the premise of small relative error, support the strength of the proposed strategy.

math.NA↗

arXiv2023

Text Classification in the Wild: a Large-scale Long-tailed Name Normalization Dataset

Real-world data usually exhibits a long-tailed distribution,with a few frequent labels and a lot of few-shot labels. The study of institution name normalization is a perfect application case showing this phenomenon. There are many institutions worldwide with enormous variations of their names in the publicly available literature. In this work, we first collect a large-scale institution name normalization dataset LoT-insts1, which contains over 25k classes that exhibit a naturally long-tailed distribution. In order to isolate the few-shot and zero-shot learning scenarios from the massive many-shot classes, we construct our test set from four different subsets: many-, medium-, and few-shot sets, as well as a zero-shot open set. We also replicate several important baseline methods on our data, covering a wide range from search-based methods to neural network methods that use the pretrained BERT model. Further, we propose our specially pretrained, BERT-based model that shows better out-of-distribution generalization on few-shot and zero-shot test sets. Compared to other datasets focusing on the long-tailed phenomenon, our dataset has one order of magnitude more training data than the largest existing long-tailed datasets and is naturally long-tailed rather than manually synthesized. We believe it provides an important and different scenario to study this problem. To our best knowledge, this is the first natural language dataset that focuses on long-tailed and open-set classification problems.

cs.CL↗

arXiv2023

An efficient topology optimization method based on adaptive reanalysis with projection reduction

Efficient topology optimization based on the adaptive auxiliary reduced model reanalysis (AARMR) is proposed to improve computational efficiency and scale. In this method, a projection auxiliary reduced model (PARM) is integrated into the combined approximation reduced model (CARM) to reduce the dimension of the model in different aspects. First, the CARM restricts the solution space to avoid large matrix factorization. Second, the PARM is proposed to construct the CARM dynamically to save computational cost. Furthermore, the multi-grid conjugate gradient method is suggested to update PARM adaptively. Finally, several classic numerical examples are tested to show that the proposed method not only significantly improves computational efficiency, but also can solve large-scale problems that are difficult to solve by direct solvers due to the memory limitations.

cs.CE↗

arXiv2022

An efficient topology optimization based on multigrid assisted reanalysis for heat transfer problem

To improve the computational efficiency of heat transfer topology optimization, a Multigrid Assisted Reanalysis (MGAR) method is proposed in this study. The MGAR not only significantly improves the computational efficiency, but also relieves the hardware burden, and thus can efficiently solve large-scale heat transfer topology optimization problems. In addition, a projection-based post-processing strategy is also proposed and integrated with a continuous density filtering strategy to successfully obtain smooth boundary while eliminating some small-sized features. Several 2D and 3D numerical examples demonstrate that the computational efficiency of the MGAR is close to or even higher than that of the MGCG with almost identical optimization results, moreover, the efficiency improvement in the 3D scenario is superior than that of the 2D scenario, which reveals the excellent potential of the MGAR to save computational cost for large-scale problems.

cs.CE↗

arXiv2022

Multi-relational Instruction Association Graph for Cross-architecture Binary Similarity Comparison

Cross-architecture binary similarity comparison is essential in many security applications. Recently, researchers have proposed learning-based approaches to improve comparison performance. They adopted a paradigm of instruction pre-training, individual binary encoding, and distance-based similarity comparison. However, instruction embeddings pre-trained on external code corpus are not universal in diverse real-world applications. And separately encoding cross-architecture binaries will accumulate the semantic gap of instruction sets, limiting the comparison accuracy. This paper proposes a novel cross-architecture binary similarity comparison approach with multi-relational instruction association graph. We associate mono-architecture instruction tokens with context relevance and cross-architecture tokens with potential semantic correlations from different perspectives. Then we exploit the relational graph convolutional network (R-GCN) to perform type-specific graph information propagation. Our approach can bridge the gap in the cross-architecture instruction representation spaces while avoiding the external pre-training workload. We conduct extensive experiments on basic block-level and function-level datasets to prove the superiority of our approach. Furthermore, evaluations on a large-scale real-world IoT malware reuse function collection show that our approach is valuable for identifying malware propagated on IoT devices of various architectures.

cs.CR↗

arXiv2022

l-Leaks: Membership Inference Attacks with Logits

Machine Learning (ML) has made unprecedented progress in the past several decades. However, due to the memorability of the training data, ML is susceptible to various attacks, especially Membership Inference Attacks (MIAs), the objective of which is to infer the model's training data. So far, most of the membership inference attacks against ML classifiers leverage the shadow model with the same structure as the target model. However, empirical results show that these attacks can be easily mitigated if the shadow model is not clear about the network structure of the target model. In this paper, We present attacks based on black-box access to the target model. We name our attack \textbf{l-Leaks}. The l-Leaks follows the intuition that if an established shadow model is similar enough to the target model, then the adversary can leverage the shadow model's information to predict a target sample's membership.The logits of the trained target model contain valuable sample knowledge. We build the shadow model by learning the logits of the target model and making the shadow model more similar to the target model. Then shadow model will have sufficient confidence in the member samples of the target model. We also discuss the effect of the shadow model's different network structures to attack results. Experiments over different networks and datasets demonstrate that both of our attacks achieve strong performance.

cs.LG↗

arXiv2021

The Complex Geometry and Representation Theory of Statistical Transformation Models

Given a measure space ${\mathcal X}$, we can construct a number of induced structures: eg. its $L^2$ space, the space ${\mathcal P}({\mathcal X})$ of probability distributions on ${\mathcal X}$. If, in addition, ${\mathcal X}$ admits a transitive measure-preserving Lie group action, natural actions are induced on those structures. We expect relationships between these induced structures and actions. We study, in particular, the relations between $L^2({\mathcal X})$ and exponential transformation models on ${\mathcal X}$, which are special "submanifolds" of ${\mathcal P}({\mathcal X})$ closed under the induced action, whose tangent bundles are Kähler manifolds (given by Molitor). Geometrically, we show the tangent bundle has, locally, the "same" Kähler metric with the Fubini-Study metric on the projectivization of $L^2({\mathcal X})$. Moreover we show the action on the tangent bundle is equivariant with that on $L^2({\mathcal X})$, which is a unitary representation. Finally, in some cases, when the symplectic action on the tangent bundle is Hamiltonian, we show that any coadjoint orbit in the image of its moment map induces, via Kirillov's correspondence from orbit method, irreducible unitary representations that are subrepresentations of the aforementioned representation in $L^2({\mathcal X})$.

math.DG↗