איתור פגיעויות: שילוב רב-מודאלי מונחה Fisher

תקציר מקורי באנגליתarXiv:2601.02438v4 Announce Type: replace-cross Abstract: Software vulnerability detection can be formulated as a binary classification problem that determines whether a given code snippet contains security defects. Existing multimodal methods typically fuse Natural Code Sequence (NCS) representations extracted by pretrained models with Code Property Graph (CPG) representations extracted by graph neural networks, under the implicit assumption that introducing an additional modality necessarily yields information gain. Through empirical analysis, we demonstrate the limitations of this assumption: pretrained models already encode substantial structural information implicitly, leading to strong overlap between the two modalities; moreover, graph encoders are generally less effective than pret