AI & ML
Protecting Web Applications using a Multimodal AI-based System for Classifying Web Injection Attacks
arXiv cs.CR0 views
arXiv:2611.23660v1 Announce Type: new Abstract: Web applications have been essential to accessing and managing online services. Made available with weaknesses, much due to their rapid development and human error, they are exposed to frequent web injection attacks, leaving security analysts overwhelmed with threats and alerts that often lack critical details for proper risk assessment. Detecting these attacks requires inspecting the payload of network traffic packets, which becomes inaccessible when traffic is encrypted via HTTPS, as encryption hides the content of the traffic. This paper introduces a Multimodal Artificial Intelligence (AI) system to protect online services that rely on web application security by detecting and classifying web injection attacks, and provides security analysts with information to support attack prevention and incident response. The system employs unsupervised Machine Learning (ML) to flag potentially anomalous Network Flows (NetFlows). The corresponding data recorded in Web Server Logs (WebLogs) is then analysed using a heuristic framework based on Natural Language Processing (NLP) and supervised ML to detect and classify web injection attacks. Finally, the resulting classifications are scrutinised using a Similarity Search Engine (SSE) based on Locality Sensitive Hashing (LSH) to validate them. The solution handles encrypted traffic by analysing NetFlows and WebLogs, the latter in their natural, unencrypted form, by leveraging NetFlow-level metadata for anomaly detection and analysing web server logs after TLS termination, thereby avoiding any additional in-network traffic decryption. It was evaluated in the classification of eight web injection attack classes. The results demonstrated its ability to accurately identify attacks and their classes, achieving an F_1 score of 91% and an accuracy of 95%, and offering valuable insights for alert prioritisation.
Source:https://arxiv.org/abs/2611.23660PreviousA-Tag: Cryptographic File Tagging with Enforced Live Human PresenceNextFlowSH: Detecting Web Attacks by Correlating Anomalous Network Flows and Endpoint Logs
Related posts

Report: Apple job listings detail plans for autonomous AI agents
09to5Mac

ChatGPT Health feature now works with Mac app, Dots, more
09to5Mac

macOS 27.3 public beta 2 now available, here’s everything new
09to5Mac

OpenAI begins testing dots with ChatGPT Plus users, expands Business access
09to5Mac
![Google homepage rolling out AI-focused redesign that includes your Gemini chats [Video]](https://9to5google.com/wp-content/uploads/sites/4/2026/11/google-search-gemini-homepage.jpg?quality=82&strip=all&w=1600)
Google homepage rolling out AI-focused redesign that includes your Gemini chats [Video]
09to5Google
Google’s 3D emoji has wild Android spec requirements: 10GB of free space, 6GB RAM
09to5Google