Direct-sequence spread spectrum (DSSS) has been recognized as an effective jamming resilient technique. However, the effectiveness of DSSS relies on the use of either pre-shared unique secret keys or a bank of public codes, which can be prohibitively expensive in future large-scale decentralized wireless networks, e.g., the Internet of Things. To tackle this problem, in this work we develop a new framework for self-controlled physical-layer-security-based spreading sequence generation. Specifically, we exploit the shared randomness inherent in wireless channels to generate and refresh secret seeds at each communicating node using shared randomness extraction, entropy pooling and random seed generation. The generated secret seeds are then utilized to perform DSSS. To evaluate the performance, we implement our framework on software defined radio platform and examine the successful transmission probability of the system under various models of broadband jamming along with an special case wherein adversary is assumed to have leaked information on key rate. Both our analysis and real-world measurements confirm that communication systems based on our framework can achieve jamming-resilient communications without requiring pre-shared sequences.