Software-Defined Network (SDN) revolutionizes traditional network structures by isolating the data plane and the control plane, which offers greater flexibility in managing network resources. Nevertheless, SDN remains vulnerable to certain threats inherited from the traditional network, including Distributed Low-rate Denial-of-Service (DLDoS) attack. This attack is more subtle and harder to detect than traditional Distributed Denial-of-Service (DDoS) attacks, because it employs a lower average attack rate. We design a real-time detection and mitigation system named DOE-DTL specifical for the DLDoS attack in SDN. For the DLDoS attack detection, we utilize Machine-Learning (ML) methods to construct a detection model and introduce it in DOE-DTL. In the construction, we leverage Extreme Learning Machine (ELM) and make a dual optimization using Whale Optimization Algorithm (WOA). For the DLDoS attack mitigation, we use double thresholds to determine the attack sources and make corresponding mitigation rules. DOE-DTL innovatively combines the Programmable Data Plane (PDP) in detection and mitigation, shifting some control plane tasks to the data plane. Performance assessments reveal that DOE-DTL ensures fast, accurate attack identification and low-latency mitigation while maintaining low resource usage.

The decoupling of SDN control plane and data plane allows control to be carried out independently, enhancing the programmability and manageability of the whole network. However, though this new architecture brings convenience for control, it also sets a pool for attacks. Due to the expensive and resource-consumption characteristics, SDN switches usually have a limited ternary content addressable memory to cache the flow rules in the data plane. Attackers can launch a space-consuming attack to maliciously preempt the flow table, forcing switches to reduce the quality of service. Among them, DDoS attacks should be taken seriously, especially the low-rate ones that have a lower attack rate with stronger concealment. In this paper, an architecture named MWD-CFM is proposed to protect against low-rate DDoS attacks in the switch flow tables. Multi-windows work collaboratively to improve detection performance. The feature of flow rules is corrected to do better classification, improving the effectiveness of attack traffic removal. Experiments based on real network topology and datasets are conducted to verify the deployment of MWD-CFM. Results prove that our architecture can greatly reduce the survival time of attack flows and ensure the availability of flow tables for legitimate services.

MOTIVATION: A key challenge in metabolomics is annotating measured spectra from a biological sample with chemical identities. Currently, only a small fraction of measurements can be assigned identities. Two complementary computational approaches have emerged to address the annotation problem: mapping candidate molecules to spectra, and mapping query spectra to molecular candidates. In essence, the candidate molecule with the spectrum that best explains the query spectrum is recommended as the target molecule. Despite candidate ranking being fundamental in both approaches, limited prior works incorporated rank learning tasks in determining the target molecule. RESULTS: We propose a novel machine learning model, Ensemble Spectral Prediction (ESP), for metabolite annotation. ESP takes advantage of prior neural network-based annotation models that utilize multilayer perceptron (MLP) networks and Graph Neural Networks (GNNs). Based on the ranking results of the MLP- and GNN-based models, ESP learns a weighting for the outputs of MLP and GNN spectral predictors to generate a spectral prediction for a query molecule. Importantly, training data is stratified by molecular formula to provide candidate sets during model training. Further, baseline MLP and GNN models are enhanced by considering peak dependencies through label mixing and multi-tasking on spectral topic distributions. When trained on the NIST 2020 dataset and evaluated on the relevant candidate sets from PubChem, ESP improves average rank by 23.7% and 37.2% over the MLP and GNN baselines, respectively, demonstrating performance gain over state-of-the-art neural network approaches. However, MLP approaches remain strong contenders when considering top five ranks. Importantly, we show that annotation performance is dependent on the training dataset, the number of molecules in the candidate set and candidate similarity to the target molecule. AVAILABILITY AND IMPLEMENTATION: The ESP code, a trained model, and a Jupyter notebook that guide users on using the ESP tool is available at https://github.com/HassounLab/ESP.

Acronym disambiguation is the process of determining the correct expansion of an acronym in given context, which can assist many downstream natural language processing tasks. Typically, existing methods on this task will directly perform semantic comparisons between the candidate expansions and the original sentence, ignoring the relevance of contextual information to expansions. To solve this issue, this paper proposes a context‐aware acronym disambiguation method with Siamese BERT network (ContextAD). First, we combine each candidate expansion with corresponding acronym’s context to form a new sentence set. Then, the new and original sentences are input into a Siamese BERT network that can obtain the semantic similarity. The new sentences and the separate candidate expansions are input into the Siamese BERT network, respectively, along with the original sentences, which can obtain another semantic similarity. Finally, the two different semantic similarities are combined to determine the most suitable expansion. We quantify the improvement of our proposed ContextAD model against a state‐of‐the‐art baseline using the public dataset of the shared tasks of acronym disambiguation (AD) held under AAAI‐2021 workshop on SDU and show that it achieves a better performance based on the same BERT model.

MOTIVATION: Despite experimental and curation efforts, the extent of enzyme promiscuity on substrates continues to be largely unexplored and under documented. Providing computational tools for the exploration of the enzyme-substrate interaction space can expedite experimentation and benefit applications such as constructing synthesis pathways for novel biomolecules, identifying products of metabolism on ingested compounds, and elucidating xenobiotic metabolism. Recommender systems (RS), which are currently unexplored for the enzyme-substrate interaction prediction problem, can be utilized to provide enzyme recommendations for substrates, and vice versa. The performance of Collaborative-Filtering (CF) RSs; however, hinges on the quality of embedding vectors of users and items (enzymes and substrates in our case). Importantly, enhancing CF embeddings with heterogeneous auxiliary data, specially relational data (e.g. hierarchical, pairwise or groupings), remains a challenge. RESULTS: We propose an innovative general RS framework, termed Boost-RS that enhances RS performance by 'boosting' embedding vectors through auxiliary data. Specifically, Boost-RS is trained and dynamically tuned on multiple relevant auxiliary learning tasks Boost-RS utilizes contrastive learning tasks to exploit relational data. To show the efficacy of Boost-RS for the enzyme-substrate prediction interaction problem, we apply the Boost-RS framework to several baseline CF models. We show that each of our auxiliary tasks boosts learning of the embedding vectors, and that contrastive learning using Boost-RS outperforms attribute concatenation and multi-label learning. We also show that Boost-RS outperforms similarity-based models. Ablation studies and visualization of learned representations highlight the importance of using contrastive learning on some of the auxiliary data in boosting the embedding vectors. AVAILABILITY AND IMPLEMENTATION: A Python implementation for Boost-RS is provided at https://github.com/HassounLab/Boost-RS. The enzyme-substrate interaction data is available from the KEGG database (https://www.genome.jp/kegg/).

Recently, the focus of dialogue state tracking has expanded from single domain to multiple domains.The task is characterized by the shared slots between domains.As the scenario gets more complex, the out-of-vocabulary problem also becomes more severe.Current models are not satisfactory for addressing the challenges of ontology integration between domains and out-of-vocabulary problems.To address the problem, we explore the hierarchical semantics of the ontology and enhance the interrelation between slots with masked hierarchical attention.In state value decoding stage, we address the out-of-vocabulary problem by combining generation method and extraction method together.We evaluate the performance of our model on two representative datasets, MultiWOZ in English and CrossWOZ in Chinese.The results show that our model yields a significant performance gain over current state-of-the-art state tracking model and it is more robust to out-of-vocabulary problem compared with other methods.

Low-rate denial of service (LDoS) attack is a derivative denial of service (DoS) attack, which reduces the quality of service in the network in the means of sending high-strength and instantaneous streams of data in cycles. Based on the above attack, we proposed a method based on adaptive shared nearest neighbor clustering and outlier factor analysis (ASNNC-OFA) to detect it, whose core idea is to calculate the traffic characteristics of network. We divide these traffic characteristic data based on shared neighbor clustering, and use the outlier factor algorithm to perform anomaly analysis on the divided data by training threshold. The experiments were carried out on NS2 and test-bed respectively, the results of them show that the detection method we proposed has low false negative rate and false positive rate, so it can effectively detect LDoS attacks.

Antibodies are capable of potently and specifically binding individual antigens and, in some cases, disrupting their functions. The key challenge in generating antibody-based inhibitors is the lack of fundamental information relating sequences of antibodies to their unique properties as inhibitors. We develop a pipeline, Antibody Sequence Analysis Pipeline using Statistical testing and Machine Learning (ASAP-SML), to identify features that distinguish one set of antibody sequences from antibody sequences in a reference set. The pipeline extracts feature fingerprints from sequences. The fingerprints represent germline, CDR canonical structure, isoelectric point and frequent positional motifs. Machine learning and statistical significance testing techniques are applied to antibody sequences and extracted feature fingerprints to identify distinguishing feature values and combinations thereof. To demonstrate how it works, we applied the pipeline on sets of antibody sequences known to bind or inhibit the activities of matrix metalloproteinases (MMPs), a family of zinc-dependent enzymes that promote cancer progression and undesired inflammation under pathological conditions, against reference datasets that do not bind or inhibit MMPs. ASAP-SML identifies features and combinations of feature values found in the MMP-targeting sets that are distinct from those in the reference sets.