{"total":26,"rows":[{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"id":"2303.09105","title":"Rethinking Model Ensemble in Transfer-based Adversarial Attacks","created":"2023-03-16","cited_by_count":89,"area":null},{"id":"2103.15263","title":"Zero-shot Adversarial Quantization","created":"2021-03-29","cited_by_count":44,"area":null},{"id":"2104.05097","title":"Pay attention to your loss: understanding misconceptions about 1-Lipschitz neural networks","created":"2021-04-11","cited_by_count":30,"area":null},{"id":"2110.03605","title":"Robust Feature-Level Adversaries are Interpretability Tools","created":"2021-10-07","cited_by_count":27,"area":null},{"id":"2111.03536","title":"A Unified Game-Theoretic Interpretation of Adversarial Robustness","created":"2021-11-05","cited_by_count":17,"area":null},{"id":"2406.10852","title":"IG2: Integrated Gradient on Iterative Gradient Path for Feature Attribution","created":"2024-06-16","cited_by_count":12,"area":null},{"id":"2110.07305","title":"DI-AA: An Interpretable White-box Attack for Fooling Deep Neural Networks","created":"2021-10-14","cited_by_count":10,"area":null},{"id":"2411.16782","title":"Scaling Laws for Black box Adversarial Attacks","created":"2024-11-25","cited_by_count":8,"area":null},{"id":"2308.01475","title":"Interpretable Machine Learning for Discovery: Statistical Challenges \\& Opportunities","created":"2023-08-02","cited_by_count":7,"area":null},{"id":"2106.09223","title":"Evaluating the Robustness of Bayesian Neural Networks Against Different Types of Attacks","created":"2021-06-17","cited_by_count":6,"area":null},{"id":"2211.10024","title":"Diagnostics for Deep Neural Networks with Automated Copy/Paste Attacks","created":"2022-11-18","cited_by_count":6,"area":null},{"id":"2103.08820","title":"EX-RAY: Distinguishing Injected Backdoor from Natural Features in Neural Networks by Examining Differential Feature Symmetry","created":"2021-03-16","cited_by_count":5,"area":null},{"id":"2212.11136","title":"It is not \"accuracy vs. explainability\" -- we need both for trustworthy AI systems","created":"2022-12-16","cited_by_count":5,"area":null},{"id":"2505.16705","title":"An Analysis of Concept Bottleneck Models: Measuring, Understanding, and Mitigating the Impact of Noisy Annotations","created":"2025-05-22","cited_by_count":5,"area":null},{"id":"2404.04662","title":"Learning Minimal Neural Specifications","created":"2024-04-06","cited_by_count":3,"area":null},{"id":"2507.11099","title":"A Survey on Interpretability in Visual Recognition","created":"2025-07-15","cited_by_count":2,"area":null},{"id":"2102.11010","title":"Resilience of Bayesian Layer-Wise Explanations under Adversarial Attacks","created":"2021-02-22","cited_by_count":1,"area":null},{"id":"2103.07364","title":"A Unified Game-Theoretic Interpretation of Adversarial Robustness","created":"2021-03-12","cited_by_count":0,"area":null},{"id":"2103.10603","title":"Noise Modulation: Let Your Model Interpret Itself","created":"2021-03-19","cited_by_count":0,"area":null},{"id":"2106.13682","title":"Prediction of Hereditary Cancers Using Neural Networks","created":"2021-06-25","cited_by_count":0,"area":null},{"id":"2110.10287","title":"Multi-concept adversarial attacks","created":"2021-10-19","cited_by_count":0,"area":null},{"id":"2305.03966","title":"Feature Chirality in Deep Learning Models","created":"2023-05-06","cited_by_count":0,"area":null},{"id":"2311.15994","title":"Adversarial Doodles: Interpretable and Human-drawable Attacks Provide Describable Insights","created":"2023-11-27","cited_by_count":0,"area":null},{"id":"2405.01855","title":"Robust Explainable Recommendation","created":"2024-05-03","cited_by_count":0,"area":null}],"next_cursor":null}