Search for: All records

As widely used in data-driven decision-making, recommender systems have been recognized for their capabilities to provide users with personalized services in many user-oriented online services, such as E-commerce (e.g., Amazon, Taobao, etc.) and Social Media sites (e.g., Facebook and Twitter). Recent works have shown that deep neural networks-based recommender systems are highly vulnerable to adversarial attacks, where adversaries can inject carefully crafted fake user profiles (i.e., a set of items that fake users have interacted with) into a target recommender system to promote or demote a set of target items. Instead of generating users with fake profiles from scratch, in this paper, we introduce a novel strategy to obtain “fake” user profiles via copying cross-domain user profiles, where a reinforcement learning-based black-box attacking framework (CopyAttack+) is developed to effectively and efficiently select cross-domain user profiles from the source domain to attack the target system. Moreover, we propose to train a local surrogate system for mimicking adversarial black-box attacks in the source domain, so as to provide transferable signals with the purpose of enhancing the attacking strategy in the target black-box recommender system. Comprehensive experiments on three real-world datasets are conducted to demonstrate the effectiveness of the proposed attacking framework. 

The operationalAeolusLevel‐2B (L2B) horizontal line‐of‐sight (HLOS) retrieved Rayleigh winds, produced by the European Space Agency (ESA), utilize European Centre for Medium‐Range Weather Forecasts (ECMWF) short‐term forecasts of temperature, pressure, and horizontal winds in the Rayleigh–Brillouin and M1 correction procedures. These model fields or backgrounds can contain ECMWF model‐specific errors, which may propagate to the retrieved Rayleigh winds. This study examines the sensitivity of the retrieved Rayleigh winds to the changes in the model backgrounds, and the potential benefit of using the same system, in this case the National Oceanic and Atmospheric Administration's Finite‐Volume Cubed Sphere Global Forecast System (FV3GFS), for both the corrections and the data assimilation and forecast procedures. It is shown that the differences in the model backgrounds (FV3GFS minus ECMWF) can propagate through the Level‐2B horizontal line‐of‐sight Rayleigh wind retrieval process, mainly the M1 correction, resulting in differences in the retrieved Rayleigh winds with mean and standard deviation of magnitude as large as 0.2 m·s⁻¹. The differences reach up to 0.4, 0.6, and 0.7 m·s⁻¹for the 95th, 99th, and 99.5th percentiles of the sample distribution with maxima of ∼1.4 m·s⁻¹. The numbers of the large differences for the combined lower and upper 5th, 1st, and 0.5th percentile pairs are ∼6,100, 1,220, and 610 between 2.5 and 25 km height globally per day respectively. The ESA‐disseminated Rayleigh wind product (based on the ECMWF corrections) already shows a significant positive impact on the FV3GFS global forecasts. In the observing system experiments performed, compared with the ESA Rayleigh winds, the use of the FV3GFS‐corrected Rayleigh winds lead to ∼0.5% more Rayleigh winds assimilated in the lower troposphere and show enhanced positive impact on FV3GFS forecasts at the day 1–10 range but limited to the Southern Hemisphere.

 

Supramolecular nanocages with inner cavities have attracted increasing attention due to their fascinating molecular aesthetics and vast number of potential applications. Even though a wide array of discrete supramolecular cages with precisely designed sizes and shapes have been established, the controlled assembly of higher-order supramolecular frameworks from discrete molecular entities still represents a formidable challenge. In this work, a novel metallo-organic cage [Zn12L4] was assembled based on a triphenylene-cored hexapod terpyridine ligand. Synchotron X-ray analysis revealed a pair of enantiomeric cages in the crystal with flexible ligands twisted clockwise or anticlockwise due to steric hindrance in the structure. Interestingly, due to the strong π–π intermolecular interaction between triphenylene units, a controlled hierarchical packing of sphere-like cages in the crystal was established having a sparse packing mode with huge channels of around 3.6 nm diameter. This research sheds light on the design of strong π–π interactions in supramolecular hierarchical packing and materials science. 

Single-atom catalysts based on metal–N4 moieties and anchored on carbon supports (defined as M–N–C) are promising for oxygen reduction reaction (ORR). Among those, M–N–C catalysts with 4d and 5d transition metal (TM4d,5d) centers are much more durable and not susceptible to the undesirable Fenton reaction, especially compared with 3d transition metal based ones. However, the ORR activity of these TM4d,5d–N–C catalysts is still far from satisfactory; thus far, there are few discussions about how to accurately tune the ligand fields of single-atom TM4d,5d sites in order to improve their catalytic properties. Herein, we leverage single-atom Ru–N–C as a model system and report an S-anion coordination strategy to modulate the catalyst’s structure and ORR performance. The S anions are identified to bond with N atoms in the second coordination shell of Ru centers, which allows us to manipulate the electronic configuration of central Ru sites. The S-anion-coordinated Ru–N–C catalyst delivers not only promising ORR activity but also outstanding long-term durability, superior to those of commercial Pt/C and most of the near-term single-atom catalysts. DFT calculations reveal that the high ORR activity is attributed to the lower adsorption energy of ORR intermediates at Ru sites. Metal–air batteries using this catalyst in the cathode side also exhibit fast kinetics and excellent stability.