Reconstructing complex reflections in real-world scenes from 2D images is essential for achieving photorealistic novel view synthesis. Existing methods that utilize environment maps to model reflections from distant lighting often struggle with high-frequency reflection details and fail to account for near-field reflections. In this work, we introduce EnvGS, a novel approach that employs a set of Gaussian primitives as an explicit 3D representation for capturing reflections of environments. These environment Gaussian primitives are incorporated with base Gaussian primitives to model the appearance of the whole scene. To efficiently render these environment Gaussian primitives, we developed a ray-tracing-based renderer that leverages the GPU’s RT core for fast rendering. This allows us to jointly optimize our model for high-quality reconstruction while maintaining real-time rendering speeds. Results from multiple real-world and synthetic datasets demonstrate that our method produces significantly more detailed reflections, achieving the best rendering quality in real-time novel view synthesis. The code is available at https://zju3dv.github.io/envgs.

servers in the Internet are vulnerable to Web attacks, to detect Web attacks, a commonly used method is to detect anomalies in the request parameters by making regular-expression-based matching rules for the parameters based on known security threats. However, such methods cannot detect unknown anomalies well and they can also be easily bypassed by using techniques like transcoding. Moreover, existing anomaly detection methods are usually based on a single HTTP request, which is easy to ignore the attack behavior within a period of time, such as brute-force password cracking attack. In this paper, we propose an unsupervised W eb S ession A nomaly D etection method called WSAD. WSAD uses ten features of web session to perform anomaly detection. After extracting the ten features, WSAD uses the DBSCAN algorithm to cluster the features of each session and outputs the outliers found in the clustering process as anomalies. We evaluate the performance of WSAD on several datasets from multiple real websites of a company. The results indicate that WSAD could detect malicious behaviors that could not be detected by Web Application Firewall, and it almost has no false positives.

Web servers in the Internet are vulnerable to Web attacks. A general way to launch Web attacks is to carry attack payloads in HTTP request parameters, e.g. SQL Injection and XSS attacks. To detect Web attacks, a commonly used method is to detect anomalies in the request parameters by making regular-expression-based matching rules for the parameters based on known security threats. However, such methods cannot detect unknown anomalies well and they can also be easily bypassed by using techniques like transcoding. Moreover, existing anomaly detection methods are usually based on supervised learning methods that require a large number of high-quality labelled samples as training sets, which are difficult to obtain in real situations. In this paper, we propose an unsupervised HTTP Request Parameter Anomaly Detection method called RPAD. RPAD uses five features of HTTP request parameters to perform anomaly detection including type, length, number of tokens, encoding type and character feature. After extracting the five features, RPAD uses the DBSCAN algorithm to cluster the parameters of each target access request and outputs the outliers found in the clustering process as anomalies. We evaluate the performance of RPAD on several datasets from multiple real websites of a Cyber Security Company. The results indicate that RPAD is highly efficient in detecting deviating abnormal parameter values with an accuracy of 99%.