While distributed acoustic sensing based on Rayleigh backscattering has been widely studied and deployed across various use cases, its adaptation in existing telecom infrastructure is fundamentally limited by inline optical amplifiers which block the backscattering light. Recently, vibration sensing based on forward transmission has emerged as a promising alternative, offering wider frequency response, higher signal-to-noise ratio, longer sensing distance, and compatibility with inline amplifiers. However, forward-transmission approach faces the challenge in signal identification and reconstruction when multiple vibration events and interference occur along the fiber simultaneously. To address this issue, we propose an equivalent dual-sensor phased array model to the bidirectional forward-transmission fiber sensing, which reformulates the problems in fiber sensing into the tasks in array processing. We introduce two beamforming techniques, including generalized sidelobe canceller (GSC) and null steering beamformer (NSBF) to reconstruct the signal of interest while suppressing noise and interference. We demonstrate the effectiveness of dual-sensor beamforming over 100km fiber experiment without amplifiers, achieving over 20 dB suppression of stationary interference using GSC and 18 dB jamming rejection using NSBF. To our knowledge, this is the first demonstration of high-fidelity signal recovery in forward-transmission sensing under strong noise and interference. This work bridges the gap between fiber sensing and adaptive array processing, opening new directions for blind source separation and integrated communication-sensing systems.