arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.01153cs.CVcs.AIcs.LG
收藏

DPAC:分布保持对抗控制用于扩散采样

DPAC: Distribution-Preserving Adversarial Control for Diffusion Sampling

Yonsei University(延世大学)

Han-Jin Lee, Han-Ju Lee, Jin-Seong Kim, Seok-Hwan Choi

AI总结:

DPAC通过在切空间上投影对抗梯度,保持分布并提升扩散采样质量,理论和实验均验证其有效性。

摘要:

对抗引导的扩散采样往往能够达到目标类别,但随着对抗控制轨迹与名义轨迹之间的偏差累积,样本质量会下降。我们正式将这种退化定义为受控与名义(未受控)扩散过程之间的路径空间Kullback-Leibler散度(路径-KL),从而通过Girsanov定理证明其恰好等于控制能量。基于这种随机最优控制(SOC)观点,我们理论证明最小化路径-KL同时收紧2-瓦尔德距离和弗雷歇 inception 距离(FID)的上界,揭示了对抗控制能量与感知保真度之间的原理性联系。从变分视角出发,我们推导了控制的最优条件:在所有产生相同分类增益的方向中,切向于等(log-)密度表面(即垂直于分数)的组件最小化路径-KL,而法向量直接增加分布漂移。这导致DPAC(分布保持对抗控制),一种扩散引导规则,将对抗梯度投影到由生成分数几何定义的切空间上。我们进一步证明,在离散求解器中,切向投影会消除瓦尔德距离中的O(Δt)主导误差项,实现O(Δt²)的质量差距;此外,它在分数或度量近似方面仍保持二阶鲁棒性。在ImageNet-100上的实验证实了理论预测,确认DPAC在匹配攻击成功率下实现了更低的FID和估计路径-KL。

英文摘要:

Adversarially guided diffusion sampling often achieves the target class, but sample quality degrades as deviations between the adversarially controlled and nominal trajectories accumulate. We formalize this degradation as a path-space Kullback-Leibler divergence(path-KL) between controlled and nominal (uncontrolled) diffusion processes, thereby showing via Girsanov's theorem that it exactly equals the control energy. Building on this stochastic optimal control (SOC) view, we theoretically establish that minimizing this path-KL simultaneously tightens upper bounds on both the 2-Wasserstein distance and Fréchet Inception Distance (FID), revealing a principled connection between adversarial control energy and perceptual fidelity. From a variational perspective, we derive a first-order optimality condition for the control: among all directions that yield the same classification gain, the component tangent to iso-(log-)density surfaces (i.e., orthogonal to the score) minimizes path-KL, whereas the normal component directly increases distributional drift. This leads to DPAC (Distribution-Preserving Adversarial Control), a diffusion guidance rule that projects adversarial gradients onto the tangent space defined by the generative score geometry. We further show that in discrete solvers, the tangent projection cancels the O(Δt) leading error term in the Wasserstein distance, achieving an O(Δt^2) quality gap; moreover, it remains second-order robust to score or metric approximation. Empirical studies on ImageNet-100 validate the theoretical predictions, confirming that DPAC achieves lower FID and estimated path-KL at matched attack success rates.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑