TriGuard：利用归因熵、验证与漂移测试模型安全性
TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift
AI总结：
针对深度神经网络在对抗与分布偏移下的可靠性难题，提出融合形式化验证、归因熵与新型归因漂移分数的TriGuard安全评估框架，可发现模型推理细微脆弱性，且熵正则化训练能在保性能的同时减少解释漂移，推动鲁棒可解释模型评估发展。
摘要：
深度神经网络通常能实现高准确率，但确保其在对抗性偏移和分布偏移下的可靠性仍是一项紧迫挑战。我们提出TriGuard，这是一个统一的安全性评估框架，结合了三大核心模块：（1）形式化鲁棒性验证；（2）用于量化显著性集中度的归因熵；（3）一种衡量解释稳定性的新型归因漂移分数（Attribution Drift Score）。TriGuard揭示了模型准确率与可解释性之间的关键不匹配：经过验证的模型仍可能表现出不稳定的推理过程，基于归因的信号能提供超越对抗准确率的补充性安全洞察。我们在三个数据集、五种架构上开展了大量实验，结果表明TriGuard能够发现神经推理中细微的脆弱性。我们进一步证明，熵正则化训练可在不牺牲性能的前提下减少解释漂移。TriGuard推动了鲁棒、可解释模型评估领域的前沿发展。
英文摘要：
Deep neural networks often achieve high accuracy, but ensuring their reliability under adversarial and distributional shifts remains a pressing challenge. We propose TriGuard, a unified safety evaluation framework that combines (1) formal robustness verification, (2) attribution entropy to quantify saliency concentration, and (3) a novel Attribution Drift Score measuring explanation stability. TriGuard reveals critical mismatches between model accuracy and interpretability: verified models can still exhibit unstable reasoning, and attribution-based signals provide complementary safety insights beyond adversarial accuracy. Extensive experiments across three datasets and five architectures show how TriGuard uncovers subtle fragilities in neural reasoning. We further demonstrate that entropy-regularized training reduces explanation drift without sacrificing performance. TriGuard advances the frontier in robust, interpretable model evaluation.
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。
