Pre-trained general-purpose language models have been a dominating component in enabling real-world natural language processing (NLP) applications. However, a pre-trained model with backdoor can be a severe threat to the applications. Most existing backdoor attacks in NLP are conducted in the fine-tuning phase by introducing malicious triggers in the targeted class, thus relying greatly on the prior knowledge of the fine-tuning task. In this paper, we propose a new approach to map the inputs containing triggers directly to a predefined output representation of the pre-trained NLP models, e.g., a predefined output representation for the classification token in BERT, instead of a target label. It can thus introduce backdoor to a wide range of downstream tasks without any prior knowledge. Additionally, in light of the unique properties of triggers in NLP, we propose two new metrics to measure the performance of backdoor attacks in terms of both effectiveness and stealthiness. Our experiments with various types of triggers show that our method is widely applicable to different fine-tuning tasks (classification and named entity recognition) and to different models (such as BERT, XLNet, BART), which poses a severe threat. Furthermore, by collaborating with the popular online model repository Hugging Face, the threat brought by our method has been confirmed. Finally, we analyze the factors that may affect the attack performance and share insights on the causes of the success of our backdoor attack. CCS CONCEPTS• Computing methodologies → Natural language processing; Transfer learning.

No abstract

Online short-term rental platforms, such as Airbnb, have been becoming popular, and a better pricing strategy is imperative for hosts of new listings. In this paper, we analyzed the relationship between the description of each listing and its price, and proposed a text-based price recommendation system called TAPE to recommend a reasonable price for newly added listings. We used deep learning techniques (e.g., feedforward network, long short-term memory, and mean shift) to design and implement TAPE. Using two chronologically extracted datasets of the same four cities, we revealed important factors (e.g., indoor equipment and high-density area) that positively or negatively affect each property's price, and evaluated our preliminary and enhanced models. Our models achieved a Root-Mean-Square Error (RMSE) of 33.73 in Boston, 20.50 in London, 34.68 in Los Angeles, and 26.31 in New York City, which are comparable to an existing model that uses more features.

Background: Renal damage and intestinal flora imbalance due to lipotoxicity are particularly significant in terms of oxidative stress and inflammation, which can be alleviated with bioactive peptides. The monkfish (Lophius litulon) is rich in proteins, which can be used as a source of quality bioactive peptides. This study aimed to examine the protective effect of monkfish peptides on renal injury and their potential role in regulating gut microbiota. Methods: Monkfish meat was hydrolyzed using neutral protease and filtered, and the component with the highest elimination rate of 2,2-diphenyl-1-picrylhydrazyl was named lophius litulon peptides (LPs). Lipid nephrotoxicity was induced via high-fat diet (HFD) feeding for 8 weeks and then treated with LPs. Oxidative stress, inflammatory factors, and intestinal flora were evaluated. Results: LP (200 mg/kg) therapy reduced serum creatinine, uric acid, and blood urea nitrogen levels by 49.5%, 31.6%, and 31.6%, respectively. Renal vesicles and tubules were considerably improved with this treatment. Moreover, the activities of superoxide dismutase, glutathione peroxidase, and total antioxidant capacity increased significantly by 198.7%, 167.9%, 61.5%, and 89.4%, respectively. LPs attenuated the upregulation of HFD-induced Toll-like receptor 4 and phospho-nuclear factor-kappa B and increased the protein levels of heme oxygenase 1, nicotinamide quinone oxidoreductase 1, and nuclear factor erythroid 2-related factor 2. The dysbiosis of intestinal microbiota improved after LP treatment. Conclusions: LPs significantly improve antioxidant activity, reduce inflammatory cytokine levels, and regulate intestinal dysbiosis. Thus, LPs are potential compounds that can alleviate HFD-induced renal lipotoxicity.

No abstract