Search

Knowledge transfer is critical in making use of data from multi-source domains, but most existing techniques are not privacy-preserving. Nowadays, data leakage, together with the advancement of big-data-driven Artificial Intelligence, has raised huge concerns over data security. The neglect of privacy makes such approaches impractical. For addressing intrusion detection tasks, the Deep Autoencoding Gaussian Mixture Model (DAGMM) concatenates and jointly optimizes a compression and an estimation network in an unsupervised manner. However, DAGMM still suffers from the lack of diversely distributed intrusion samples in real-life scenarios where organizations are neither willing nor legally allowed to engage in data sharing. Given the increasing public concern over data privacy and scandals, federated learning which only allows model parameter sharing is thus proposed to enhance model performance while preserving data privacy. Moreover, it also addresses the competitive concerns on the part of organizations when sharing data with their rivals. This study proposes a Federated Deep Autoencoding Gaussian Mixture Model (F-DAGMM) to build up privacy-preserving knowledge transfer, to further support inter-organizational cooperation and high-level decision making. A two-phase federated optimization strategy is proposed to address the performance degradation caused by the significant differences in the individual clients’ data distributions. Extensive experiments demonstrate the superiority of the proposed F-DAGMM. Nanyang Technological University This work is supported in part by Grant No. NTU 04INS000471C130 and in part by the RIE2020 Industry Alignment Fund - Industry Collaboration Projects (IAF-ICP) Funding Initiative, as well as cash and in-kind contribution from Singapore Telecommunications Limited (Singtel), through Singtel Cognitive and Artificial Intelligence Lab for Enterprises (SCALE@NTU).

Additional file 1: Fig. S1. Chemical structure of SS-ATS and number of carbon atoms in SS-ATS. Fig. S2. Chemical structure of TPP-SS-ATS and number of carbon atoms in TPP-SS-ATS. Fig. S3. Mass spectrum of SS-ATS. Fig. S4. Mass spectrum of TPP-SS-ATS. Fig. S5. 1H NMR spectrum of SS-ATS. Fig. S6. 1H NMR spectrum of TPP-SS-ATS. Fig. S7. 13C NMR spectrum of TPP-SS-ATS. Fig. S8. HSQC spectrum of TPP-SS-ATS. Fig. S9. HMBC spectrum of TPP-SS-ATS. Fig. S10. Purity check of TPP-SS-ATS chromatogram. Fig. S11. Ultraviolet spectrogram of TPP-SS-ATS. Fig. S12. Molecular dynamics simulation. Fig. S13. The hemolytic results of TPP-SS-ATS-LS. Fig. S14. Effect of TPP-SS-ATS -LS on oxygen consumption rate (OCR) of human breast MCF-7 cells. Fig. S15. Effect of TPP-SS-ATS-LS on oxygen consumption rate (OCR) of mouse breast 4T1 cells. Table S1. Result of TPP-SS-ATS purity check.

Additional file 1: Figure S1. TEM imaging of sSiO2 NPs. Figure S2. N2 adsorption/desorption isotherms and pore-size distribution curve of the as-synthesized H-mMnO2 NPs. Figure S3. EDS analysis of the AHTPR NPs. Figure S4. The dispersity and stability of the AHTPR NPs. a The dispersity of the AHTPR NPs was monitored in different media (water, ��-MEM culture medium with or without 10% FBS) over a prolonged incubation time up to 7 days. b Hydrodynamic size variation of the AHTPR NPs dispersed in water, ��-MEM culture medium with or without 10% FBS. Figure S5. Temperature variation curves of the different formulations (PBS, H-mMnO2, and HTPR) irradiated by an 808 nm laser (1 W��cm���2, 10 min). Figure S6. Photothermal-conversion performance of AHTPR NPs. (a) Photothermal performance of AHTPR NPs aqueous solution (120 ��g mL���1) under 808 nm laser (1.0 W cm���2) irradiation. (b) Fitted linear relationship between time and ��� ln �� obtained from the cooling period of (a). Figure S7. The standard curve of AIBI determined by a UV���VIS spectrophotometer. Figure S8. The cellular uptake of ICG@HTPR NPs by MNNG/HOS cells under different conditions (chlorpromazine, genistein, amiloride, and cytochalasin D, 4 ��C). Cells treated with ICG@HTPR NPs at 37 ��C served as the control group. (* P

We present an interesting and challenging dataset that features a large number of scenes with messy tables captured from multiple camera views. Each scene in this dataset is highly complex, containing multiple object instances that could be identical, stacked and occluded by other instances. The key challenge is to associate all instances given the RGB image of all views. The seemingly simple task surprisingly fails many popular methods or heuristics that we assume good performance in object association. The dataset challenges existing methods in mining subtle appearance differences, reasoning based on contexts, and fusing appearance with geometric cues for establishing an association. We report interesting findings with some popular baselines, and discuss how this dataset could help inspire new problems and catalyse more robust formulations to tackle real-world instance association problems. Project page: $\href{https://caizhongang.github.io/projects/MessyTable/}{\text{MessyTable}}$, Comment: Accepted in ECCV 2020