Tootfinder

Transferable Direct Prompt Injection via Activation-Guided MCMC Sampling
Minghui Li, Hao Zhang, Yechao Zhang, Wei Wan, Shengshan Hu, pei Xiaobing, Jing Wang
https://arxiv.org/abs/2509.07617

Transferable Direct Prompt Injection via Activation-Guided MCMC Sampling
Direct Prompt Injection (DPI) attacks pose a critical security threat to Large Language Models (LLMs) due to their low barrier of execution and high potential damage. To address the impracticality of existing white-box/gray-box methods and the poor transferability of black-box methods, we propose an activations-guided prompt injection attack framework. We first construct an Energy-based Model (EBM) using activations from a surrogate model to evaluate the quality of adversarial prompts. Guided b…

DPI-SPR: A Differentiable Physical Inversion for Shadow Profile Reconstruction Framework in Forward Scatter Radar
ShuQi Lei, Gan Yu, Yuan Tian, XiaoWei Shao
https://arxiv.org/abs/2508.11470

DPI-SPR: A Differentiable Physical Inversion for Shadow Profile Reconstruction Framework in Forward Scatter Radar
Forward scatter radar (FSR) has emerged as an effective imaging modality for target detection, utilizing forward scattering (FS) signals to reconstruct two-dimensional shadow profile images of objects. However, real-world FS signals are inevitably corrupted by noise. Due to the ill-posed nature of electromagnetic inversion and its high sensitivity to noise, existing imaging methods often suffer from degraded performance or even complete failure under low signal-to-noise ratio (SNR) conditions. …