鸟类看起来像汽车：对内在可解释深度学习的对抗分析
Birds look like cars: Adversarial analysis of intrinsically interpretable deep learning
AI总结：
本文研究了内在可解释深度学习模型的对抗性风险，通过原型操纵和后门攻击揭示其不可解释性，并探讨了提升模型鲁棒性和对齐性的必要性。
摘要：
一种常见的观点是，内在可解释的深度学习模型能够确保对其行为的正确、直观的理解，并在对抗性错误或故意操纵下具有更大的鲁棒性。然而，这些观点尚未得到全面验证，越来越多的证据对其提出质疑。在本文中，我们强调了过度依赖和对对抗性操纵的易受攻击性相关的风险，这些所谓的“内在（即本质上）可解释”模型由设计决定。我们介绍了两种对抗分析策略，包括针对基于原型的网络的原型操纵和后门攻击，并讨论了概念瓶颈模型如何防御这些攻击。通过利用模型使用潜在原型来欺骗其推理，展示了深度神经网络固有的不可解释性，导致一种被视觉确认偏见强化的错误安全感。所报告的部分原型网络的局限性对其可信度和适用性提出了质疑，推动了对（深度）可解释模型鲁棒性和对齐性的进一步研究。
英文摘要：
A common belief is that intrinsically interpretable deep learning models ensure a correct, intuitive understanding of their behavior and offer greater robustness against accidental errors or intentional manipulation. However, these beliefs have not been comprehensively verified, and growing evidence casts doubt on them. In this paper, we highlight the risks related to overreliance and susceptibility to adversarial manipulation of these so-called "intrinsically (aka inherently) interpretable" models by design. We introduce two strategies for adversarial analysis with prototype manipulation and backdoor attacks against prototype-based networks, and discuss how concept bottleneck models defend against these attacks. Fooling the model's reasoning by exploiting its use of latent prototypes manifests the inherent uninterpretability of deep neural networks, leading to a false sense of security reinforced by a visual confirmation bias. The reported limitations of part-prototype networks put their trustworthiness and applicability into question, motivating further work on the robustness and alignment of (deep) interpretable models.
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。
