Deep learning models are known to be vulnerable not only to input-dependent adversarial attacks but also to input-agnostic or universal adversarial attacks. Dezfooli et al. [8,9] construct universal adversarial attack on a given model by looking at a large number of training data points and the geometry of the decision boundary near them. Subsequent work [5] constructs universal attack by looking only at test examples and intermediate layers of the given model. In this paper, we propose a simple universalization technique to take any input-dependent adversarial attack and construct a universal attack by only looking at very few adversarial test examples. We do not require details of the given model and have negligible computational overhead for universalization.We theoretically justify our universalization technique by a spectral property common to many input-dependent adversarial perturbations, e.g., gradients, Fast Gradient Sign Method (FGSM) and DeepFool. Using matrix concentration inequalities and spectral perturbation bounds, we show that the top singular vector of input-dependent adversarial directions on a small test sample gives an effective and simple universal adversarial attack. For VGG16 and VGG19 models trained on ImageNet, our simple universalization of Gradient, FGSM, and DeepFool perturbations using a test sample of 64 images gives fooling rates comparable to state-of-the-art universal attacks [8,5] for reasonable norms of perturbation.
Objective: The objective of the present work was to study the use of the sintering technique, a relatively new concept in pharmaceutical sciences, in the development of mucoadhesive buccal tablets for ivabradine Hydrochloride.
Methods: The method consisted of blending drug, hydroxypropyl methylcellulose (HPMC K100M), carnauba wax, and other excipients followed by direct compression into tablets. The compressed fluffy matrices were sintered at two different constant temperatures like 50 °C and 60 °C for two different periods like 1.5 h and 3 h in a hot air oven. The effect of sintering on tensile strength, dissolution profile, and other parameters were studied. The drug-polymer-excipient compatibility was evaluated by Fourier transform Infrared (FTIR) and differential scanning calorimetric (DSC) studies.
Results: The sintering condition markedly affected the drug release properties, hardness, and friability of the tablets. Based on the f2 similarity factor value, Ex-vivo mucoadhesive strength, Ex-vivo residence time, and in vitro dissolution studies, formulation F3SD was selected as an optimized formulation. Drug release followed a non-Fickian diffusion mechanism with the Higuchi model release kinetics. Stability studies of mucoadhesive buccal tablets in normal human saliva indicated the stability of the drug and buccal tablet in the oral cavity. Stability studies as per ICH guidelines revealed that optimized formulation was stable on storage conditions.
Conclusion: The sintering technique provides a significant and convenient method for the development of a controlled release dosage form that can be used in the design of mucoadhesive buccal tablets of Ivabradine HCL.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.