At the very beginning of the new decade, the COVID-19 pandemic has badly hit the globe. SARS-CoV-2, the causative agent of COVID-19 carries dozens of new mutations in its genome. Multiple countries are now in the race to find a defined treatment and vaccine against COVID-19. Herein, we made an effort to find antiviral peptides against SARS-CoV-2. Gladly, with the help of Machine Learning algorithms and Supported Vector Machine, we have found three potential antiviral peptides against SARS-CoV-2. Antiviral peptides namely, Seq12 and Seq12m showed very low cytotoxicity. All antiviral peptides were able to block the RBD of the spike glycoprotein. Besides, antiviral peptides retain their properties even in case of in silico multi-point mutant models (Rosetta and FoldX based) of RBD. Moreover, Seq12, Seq12m, and Seq13m can bind with the viral membrane protein (M) and eventually interfere with viral re-packaging. In conclusion, this study suggests Seq12, Seq12m, and Seq13m holds the potential for possible therapeutics use after formal clinical trials. Besides, these antiviral peptides could aid a new diagnostic tool.