• Donga Deepika
• Chukka Sandhya Satya Sai Padmini
• Eepi Vanya
• Addala Naga Satya Manikanta
• Kothapalli Jaya Naga Sai Sriram

Web applications remain prime targets for cyber-attacks due to their widespread accessibility and inherent vulnerabilities. Conventional intrusion detection systems (IDS) are unsuitable for dynamic production situations because they mostly rely on manually created features and supervised learning models, which need a great deal of domain knowledge and labeled data. This study uses the Robust Software Modeling Tool (RSMT) to present a novel end-to-end deep learning method for automatically identifying web threats. The suggested method reconstructs call graphs to find anomalies through reconstruction errors and uses a stacked denoising autoencoder to generate low-dimensional representations from unlabeled runtime data. This approach avoids the need for labeled datasets by using an unsupervised/semi-supervised learning paradigm, which makes it possible to detect sophisticated attack patterns like SQL injection, cross-site scripting, and deserialization vulnerabilities with ease. The system's capacity to attain high detection accuracy with little domain knowledge is demonstrated by empirical evaluation on both synthetic and production datasets. The findings demonstrate how deep learning can automate feature extraction and anomaly recognition, thereby revolutionizing intrusion detection. This work makes a substantial contribution to the field by offering a domain-agnostic, scalable solution to web security problems.

Web Security, Intrusion Detection, Deep Learning, Autoencoders, Anomaly Detection, Cybersecurity.

"Detecting Web Attacks with End-to-End Deep Learning ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 3, page no.d621-d633, March-2025, Available :http://www.jetir.org/papers/JETIR2503369.pdf

"Detecting Web Attacks with End-to-End Deep Learning ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 3, page no. ppd621-d633, March-2025, Available at : http://www.jetir.org/papers/JETIR2503369.pdf