Evidence · DiggingBeagle record
WADE: An LSTM-Based Anomaly Detection Engine for WebAssembly Applications
WADE: An LSTM-Based Anomaly Detection Engine for WebAssembly Applications
- Source role
- primary disclosure
Evidence record
WADE: An LSTM-Based Anomaly Detection Engine for WebAssembly Applications
Claim-level citations (2)
- supportsWADE learns WebAssembly execution patterns to flag abnormal function-call paths: WADE uses benign function-call traces to train a distinct LSTM behavioral baseline per WebAssembly application, so its reported zero missed attacks is bounded to 67 tested applications and ten vulnerability classes.
Abstract, application-specific LSTM and evaluated vulnerability classes
- supportsWADE learns WebAssembly execution patterns to flag abnormal function-call paths: WADE collects benign WebAssembly function-level execution sequences and uses an LSTM anomaly detector to flag deviations. The authors report evaluation across 67 Wasm applications and ten vulnerability classes, with zero observed false negatives and a 0.42 percent false positive rate on that dataset.
Abstract: LSTM trace monitoring, 67 applications, ten vulnerability classes, zero false negatives and 0.42 percent false positives