changed header photo

app.py

@@ -7,7 +7,7 @@ os.environ['DISPLAY'] = ':0'
 css = """"""
 
 with gr.Blocks(css=css) as ui:
-    gr.Image("images/header.png", min_width=1500, height=80, show_download_button=False, show_label=False)
+    gr.Image("images/header.jpg", min_width=1500, height=80, show_download_button=False, show_label=False)
     gr.HTML(value="<h2>Harnessing Large Language Models to Secure Smart Contracts</h2>")
     gr.HTML(value="<font size=\"+0.5\"><p>Smart contracts are revolutionizing many industries, but vulnerabilities in their code can lead to significant financial losses. The <a href=\"https://arxiv.org/pdf/2310.01152.pdf\">paper</a> explores how Large Language Models (LLMs) can be used to detect these vulnerabilities in smart contracts. In this static webpage, we discuss the same briefly, and link to a GUI that can help visualise the flow in a much lucid way along with a report that entends the ideas presented in the paper. To continue, LLMs are a type of artificial intelligence that can process and understand massive amounts of text data.  The authors propose a new approach,  GPTLENS, that leverages LLMs to identify potential weaknesses in smart contract code.</p><font>")
     gr.HTML(value="<font size=\"+0.5\"><p>The main thing to keep in mind in order to successfully discover as many vulnerabilities as possible is to maximize the true positives and minimize the false positives. To tackle this imbalance, GPTLens proposes an adverserial model that consists of two stages - Generative and Discriminative. In the mentioned stages, the GPT, most commonly GPT 4, plays both the roles of an AUDITOR and a CRITIC. The goal of AUDITOR is to yield a broad spectrum of vulnerabilities with the hope of encompassing the correct answer, whereas the goal of CRITIC that evaluates the validity of identified vulnerabilities is to minimize the number of false positives.  Compared to exisitng models in the market, GPTLens has some key advantages, some of the key benefits of using LLMs for smart contract vulnerability detection are as below :</p><font>")