Search

Vulnerability prediction, in which static analysis is leveraged to predict the vulnerabilities of binary programs, has become a popular research topic. Traditional vulnerability prediction methods depend on vulnerability patterns, which must be predefined by security experts in a time-consuming manner. The development of Artificial Intelligence (AI) has yielded new options for vulnerability prediction. Neural networks allow vulnerability patterns to be learned automatically. However, current works extract only one or two types of features and use traditional models such as word2vec, which results in the loss of much instruction-level information. In this paper, we propose a model named SAViP to predict vulnerabilities in binary programs. To fully extract binary information, we integrate three kinds of features: semantic, statistical, and structural features. For semantic features, we apply the Masked Language Model (MLM) pre-training task of the RoBERTa model to the assembly code to build our language model. Using this model, we innovatively combine the beginning token and the operation-code token to create the instruction embedding. For the statistical features, we design a 56-dimensional feature vector that contains 43 kinds of instructions. For the structural features, we improve the ability of the structure2vec network to obtain the characteristic of the network by emphasizing node self-attention. Through these optimizations, we significantly increase the accuracy of vulnerability prediction over existing methods. Our experiments show that SAViP achieves a recall of 77.85% and Top 100∼600 accuracies all above 95%. The results are 10% and 13% higher than those of the state-of-the-art V-Fuzz, respectively. [ABSTRACT FROM AUTHOR]

Lactobacillus rhamnosus GG (LGG), a model probiotic strain, plays an important role in immune regulatory activity to prevent and treat intestinal inflammation or diarrhea. However, the effect of the immune modulation of LGG on macrophages to prevent Salmonella infection has not been thoroughly studied. In this study, C57BL/6 mice were pre-administered LGG for 7 days continuously, and then infected with Salmonella enterica subsp. enterica serovar Typhimurium (S. Typhimurium). The results of the in vivo study indicated that LGG could reduce body weight loss, death rate and intestinal inflammatory response caused by S. Typhimurium. LGG also limited S. Typhimurium dissemination to liver and spleen, and thereby protected against infection. In vitro study, we observed that LGG enhanced the phagocytic and bactericidal ability of macrophages and upregulated M1 macrophage characters (e.g. iNOS, NO and IL-12) against S. Typhimurium. In addition, LGG also elevated IL-10 secretion, which was helpful to ameliorate intestinal inflammatory injury caused by S. Typhimurium. In conclusion, LGG could modulate M1 macrophage polarization and offer protective effects against S. Typhimurium infection. • C57BL/6 mice pre-treated with LGG could resist S. Typhimurium infection through evaluation of bodyweight loss, survival rate, and bacterial loads in liver or spleen. • LGG was also observed to upregulate IL-10-expression and ameliorate intestinal inflammatory injury caused by S. Typhimurium through pathological evaluation, at late stage of S. Typhimurium infection. • LGG modulate M1 macrophage polarization through increasing iNOS, NO and IL-12-expression, at early stage of S. Typhimurium. [ABSTRACT FROM AUTHOR]

Macrophage polarization affects the progression of pathogenic bacterial infections. Lactobacillus is widely used to interact with macrophages and to exert specific immunomodulatory activities. In this study, we investigated the regulation of macrophage polarization against Salmonella enterica serotype Typhimurium (STM) by Lactobacillus plantarum JL01 (LP), to explore prevention and treatment strategies for salmonellosis. We assessed the in vitro differential polarization of RAW 264.7 macrophages and mouse bone marrow macrophages (BMMs) by LP against STM, by measuring protein and cytokine levels, and bactericidal activity. In addition, we assessed the protective effects of LP against STM by evaluating weight loss, survival, the burden of STM in tissues, the polarization of macrophages in the spleen and mesenteric lymph nodes (MLNs), intestinal histopathology, and cytokine production. LP slightly affected the polarization of RAW 264.7, a slight M1-skewing. LP promoted the RAW 264.7 bactericidal activity against STM. In BMMs, M1 polarization induced by LP was significantly lower than the M1-positive phenotype. The combination of LP with M1 synergistically improved M1 polarization and bactericidal activity against STM compared to the individual effects. LP promoted the activation of the NF-κB signaling pathway. Supplementation with the NF-κB inhibitor decreased M1 polarization induced by LP. We observed the protective effect of LP against STM in C57BL/6 mice, through a decrease in weight loss, mortality, STM burden in the liver, and promotion of macrophage M1 and M2 polarization in the spleen and MLNs; though M1 was higher, it did not cause inflammatory damage. In summary, LP can synergistically promote M1 polarization in combination with the M1 phenotype through the NF-κB signaling pathway and increases resistance against S . Typhimurium infection. These findings will lay the foundation for the prevention and treatment of S . Typhimurium infections in the future., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. The Reviewer JQ declared a shared affiliation with the authors at the time of the review., (Copyright © 2022 Duan, Liu, Shi, Sun, Tang, Wang and Hu.)