隐私保护的深度联合信源信道编码与环路内概念擦除

中文摘要 AI 辅助

深度联合信源信道编码（DeepJSCC）高效传输学习到的语义特征，但可能泄露性别、种族或说话者身份等敏感属性。我们提出LEAPSC（语义通信中环路内LEACE隐私保护），其核心贡献是在变分信息瓶颈（VIB）编码器内集成环路内最小二乘概念擦除（LEACE）。通过在训练期间周期性地重新拟合投影算子，LEAPSC将编码器动态与擦除机制耦合，在拟合样本上驱动每个任务标签组内的属性条件均值差异趋近于零。其他组件，即条件风险价值（CVaR）尾部敏感隐私、特征级线性调制（FiLM）信噪比条件化以及拉格朗日对偶上升，提高了跨信道条件和高泄漏样本尾部的鲁棒性。在CelebA、FairFace和Google Speech Commands上，LEAPSC分别达到0.862、0.755和0.925的任务准确率，攻击者准确率在CelebA上达到或低于仅标签基线（0.548对比基线0.580），在其他数据集上处于随机水平2个百分点（pp）以内，在匹配的52轮训练预算下，相比信息瓶颈对抗基线（IBAL）分别提高了+3.6、+2.5和+1.3个百分点（Welch's t检验，CelebA上p=0.019）。

英文摘要

Deep joint source-channel coding (DeepJSCC) transmits learned semantic features efficiently but can leak sensitive attributes such as gender, race, or speaker identity. We propose LEAPSC (LEACE-in-the-loop privacy for semantic communication), whose core contribution is the integration of in-loop least-squares concept erasure (LEACE) within a variational information bottleneck (VIB) encoder. By periodically refitting the projection operator during training, LEAPSC couples the encoder dynamics to the erasure mechanism, driving attribute-conditional mean differences toward zero within each task-label group on the fitting sample. Additional components, namely conditional value-at-risk (CVaR) tail-sensitive privacy, feature-wise linear modulation (FiLM) signal-to-noise ratio conditioning, and Lagrangian dual ascent, improve robustness across channel conditions and over the high-leakage tail of samples. On CelebA, FairFace, and Google Speech Commands, LEAPSC reaches task accuracy of 0.862, 0.755, and 0.925 respectively, with attacker accuracy at or below the label-only floor on CelebA (0.548 vs. floor 0.580) and within 2 percentage points (pp) of chance elsewhere, improving over an information-bottleneck adversarial baseline (IBAL) at a matched 52-epoch budget by +3.6, +2.5, and +1.3 pp (Welch's t-test, p=0.019 on CelebA).

发表机构

• American University of Beirut（贝鲁特美国大学）

机构由 AI 辅助整理，请以论文原文为准。