Tongrun Xing, Yongjun Dai, Xuan Liao, Zhiwen Zhang, Tong Zhou, Longlong Zhang, Tian Jiang · 2026 · arXiv
DOI: 10.48550/arXiv.2610.27585 · open-access PDF
Tandis que les radars cognitifs évoluent vers le traitement end-to-end de séquences de bande de base complexes unidimensionnelles, les réseaux profonds font face à de graves menaces adversaires. Cependant, les attaques existantes rencontrent des limitations doubles dans la guerre électronique pratique: faible transférabilité de l'architecture et vulnérabilité sévère aux distorsions des canaux physiques, ce qui dégrade leur fiabilité tactique. Pour surmonter ces barrières, nous proposons une attaque spatiale segmentée prédominante (SSTA) physique.
Machine translation (Meta M2M100); the English original follows.
As cognitive radars evolve towards the end-to-end processing of one-dimensional complex baseband sequences, deep networks face severe adversarial threats. However, existing attacks encounter dual limitations in practical electronic warfare: low cross-architecture transferability and severe vulnerability to physical channel distortions, which degrades their tactical reliability. To overcome these bottlenecks, we propose a physical prior-driven Segmented Spatio-Temporal Attack (SSTA). First, a global-local feature decoupling segmentation mechanism interrupts the adversarial gradients' dependence
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.27585, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange