{"total":74,"rows":[{"id":"2106.09249","title":"Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attacks","created":"2021-06-17","cited_by_count":101,"area":"driving"},{"id":"2107.06641","title":"Trustworthy AI: A Computational Perspective","created":"2021-07-12","cited_by_count":93,"area":null},{"id":"2212.14315","title":"\"Real Attackers Don't Compute Gradients\": Bridging the Gap Between Adversarial ML Research and Practice","created":"2022-12-29","cited_by_count":56,"area":null},{"id":"2501.15463","title":"Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values?","created":"2025-01-26","cited_by_count":51,"area":null},{"id":"2306.06123","title":"Adversarial attacks and defenses in explainable artificial intelligence: A survey","created":"2023-06-06","cited_by_count":48,"area":null},{"id":"2308.11894","title":"Does Physical Adversarial Example Really Matter to Autonomous Driving? Towards System-Level Effect of Adversarial Object Evasion Attack","created":"2023-08-23","cited_by_count":37,"area":null},{"id":"2111.09999","title":"TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systems","created":"2021-11-19","cited_by_count":36,"area":null},{"id":"2208.09418","title":"SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretability","created":"2022-08-19","cited_by_count":28,"area":null},{"id":"2410.09087","title":"Mechanistic?","created":"2024-10-07","cited_by_count":25,"area":"mechinterp"},{"id":"2208.10605","title":"SoK: Explainable Machine Learning for Computer Security Applications","created":"2022-08-22","cited_by_count":20,"area":null},{"id":"2409.09586","title":"ValueCompass: A Framework for Measuring Contextual Value Alignment Between Human and LLMs","created":"2024-09-15","cited_by_count":20,"area":"alignment"},{"id":"2206.07144","title":"Efficiently Training Low-Curvature Neural Networks","created":"2022-06-14","cited_by_count":19,"area":null},{"id":"2108.03388","title":"Jointly Attacking Graph Neural Network and its Explanations","created":"2021-08-07","cited_by_count":18,"area":null},{"id":"2109.11495","title":"DeepAID: Interpreting and Improving Deep Learning-based Anomaly Detection in Security Applications","created":"2021-09-23","cited_by_count":18,"area":null},{"id":"2301.02437","title":"Valid P-Value for Deep Learning-Driven Salient Region","created":"2023-01-06","cited_by_count":17,"area":null},{"id":"2105.12837","title":"Fooling Partial Dependence via Data Poisoning","created":"2021-05-26","cited_by_count":16,"area":"safety"},{"id":"2208.09967","title":"Inferring Sensitive Attributes from Model Explanations","created":"2022-08-21","cited_by_count":15,"area":null},{"id":"2312.09520","title":"SlowTrack: Increasing the Latency of Camera-based Perception in Autonomous Driving Using Adversarial Examples","created":"2023-12-15","cited_by_count":15,"area":null},{"id":"2211.14860","title":"Foiling Explanations in Deep Neural Networks","created":"2022-11-27","cited_by_count":14,"area":null},{"id":"2108.05075","title":"Jujutsu: A Two-stage Defense against Adversarial Patch Attacks on Deep Neural Networks","created":"2021-08-11","cited_by_count":13,"area":null},{"id":"2308.05362","title":"FINER: Enhancing State-of-the-art Classifiers with Feature Attribution to Facilitate Security Analysis","created":"2023-08-10","cited_by_count":12,"area":null},{"id":"2212.04454","title":"XRand: Differentially Private Defense against Explanation-Guided Attacks","created":"2022-12-08","cited_by_count":11,"area":null},{"id":"2107.01943","title":"When and How to Fool Explainable Models (and Humans) with Adversarial Examples","created":"2021-07-05","cited_by_count":10,"area":null},{"id":"2111.14651","title":"Multi-objective Explanations of GNN Predictions","created":"2021-11-29","cited_by_count":10,"area":null},{"id":"2305.12351","title":"Are Your Explanations Reliable? Investigating the Stability of LIME in Explaining Text Classifiers by Marrying XAI and Adversarial Attack","created":"2023-05-21","cited_by_count":10,"area":null},{"id":"2309.01866","title":"Efficient Query-Based Attack against ML-Based Android Malware Detection under Zero Knowledge Setting","created":"2023-09-05","cited_by_count":10,"area":null},{"id":"2407.04370","title":"Regulating Model Reliance on Non-Robust Features by Smoothing Input Marginal Density","created":"2024-07-05","cited_by_count":10,"area":null},{"id":"2201.02445","title":"Negative Evidence Matters in Interpretable Histology Image Classification","created":"2022-01-07","cited_by_count":8,"area":null},{"id":"2201.02715","title":"Low-Rank Constraints for Fast Inference in Structured Models","created":"2022-01-08","cited_by_count":8,"area":null},{"id":"2102.05241","title":"Detecting Localized Adversarial Examples: A Generic Approach using Critical Region Analysis","created":"2021-02-10","cited_by_count":7,"area":null},{"id":"2209.01782","title":"\"Is your explanation stable?\": A Robustness Evaluation Framework for Feature Attribution","created":"2022-09-05","cited_by_count":7,"area":null},{"id":"2210.17376","title":"SoK: Modeling Explainability in Security Analytics for Interpretability, Trustworthiness, and Usability","created":"2022-10-31","cited_by_count":7,"area":null},{"id":"2106.15820","title":"Explanation-Guided Diagnosis of Machine Learning Evasion Attacks","created":"2021-06-30","cited_by_count":6,"area":null},{"id":"2312.04542","title":"SoK: Unintended Interactions among Machine Learning Defenses and Risks","created":"2023-12-07","cited_by_count":6,"area":null},{"id":"2404.00673","title":"A Survey of Privacy-Preserving Model Explanations: Privacy Risks, Attacks, and Countermeasures","created":"2024-03-31","cited_by_count":6,"area":null},{"id":"2406.05810","title":"ControlLoc: Physical-World Hijacking Attack on Visual Perception in Autonomous Driving","created":"2024-06-09","cited_by_count":6,"area":null},{"id":"2409.09860","title":"Revisiting Physical-World Adversarial Attack on Traffic Sign Recognition: A Commercial Systems Perspective","created":"2024-09-15","cited_by_count":6,"area":null},{"id":"2211.04780","title":"On the Robustness of Explanations of Deep Neural Network Models: A Survey","created":"2022-11-09","cited_by_count":5,"area":null},{"id":"2406.06417","title":"Explainable Graph Neural Networks Under Fire","created":"2024-06-10","cited_by_count":5,"area":null},{"id":"2204.09498","title":"Backdooring Explainable Machine Learning","created":"2022-04-20","cited_by_count":4,"area":null},{"id":"2211.15926","title":"Interpretations Cannot Be Trusted: Stealthy and Effective Adversarial Perturbations against Interpretable Deep Learning","created":"2022-11-29","cited_by_count":4,"area":null},{"id":"2308.15692","title":"Intriguing Properties of Diffusion Models: An Empirical Study of the Natural Attack Capability in Text-to-Image Generative Models","created":"2023-08-30","cited_by_count":4,"area":"diffusion"},{"id":"2506.15499","title":"Pixel-level Certified Explanations via Randomized Smoothing","created":"2025-06-18","cited_by_count":4,"area":null},{"id":"2602.08567","title":"ValueFlow: Measuring the Propagation of Value Perturbations in Multi-Agent LLM Systems","created":"2026-02-09","cited_by_count":4,"area":"agents"},{"id":"2103.11526","title":"ExAD: An Ensemble Approach for Explanation-based Adversarial Detection","created":"2021-03-22","cited_by_count":3,"area":null},{"id":"2206.12284","title":"Robustness of Explanation Methods for NLP Models","created":"2022-06-24","cited_by_count":3,"area":null},{"id":"2406.05800","title":"SlowPerception: Physical-World Latency Attack against Visual Perception in Autonomous Driving","created":"2024-06-09","cited_by_count":3,"area":null},{"id":"2201.05071","title":"Evaluation of Neural Networks Defenses and Attacks using NDCG and Reciprocal Rank Metrics","created":"2022-01-10","cited_by_count":2,"area":null},{"id":"2212.05327","title":"Identifying the Source of Vulnerability in Explanation Discrepancy: A Case Study in Neural Text Classification","created":"2022-12-10","cited_by_count":2,"area":null},{"id":"2307.11906","title":"Unveiling Vulnerabilities in Interpretable Deep Learning Systems with Query-Efficient Black-box Attacks","created":"2023-07-21","cited_by_count":2,"area":null},{"id":"2309.05679","title":"Good-looking but Lacking Faithfulness: Understanding Local Explanation Methods through Trend-based Testing","created":"2023-09-09","cited_by_count":2,"area":null},{"id":"2408.01715","title":"Joint Universal Adversarial Perturbations with Interpretations","created":"2024-08-03","cited_by_count":2,"area":null},{"id":"2409.05208","title":"Influence-based Attributions can be Manipulated","created":"2024-09-08","cited_by_count":2,"area":null},{"id":"2101.09301","title":"i-Algebra: Towards Interactive Interpretability of Deep Neural Networks","created":"2021-01-22","cited_by_count":1,"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":"2307.06484","title":"Single-Class Target-Specific Attack against Interpretable Deep Learning Systems","created":"2023-07-12","cited_by_count":1,"area":null},{"id":"2307.06496","title":"Microbial Genetic Algorithm-based Black-box Attack against Interpretable Deep Learning Systems","created":"2023-07-13","cited_by_count":1,"area":null},{"id":"2510.04245","title":"Concept-Based Masking: A Patch-Agnostic Defense Against Adversarial Patch Attacks","created":"2025-10-05","cited_by_count":1,"area":null},{"id":"2602.12134","title":"Value Alignment Tax: Measuring Value Trade-offs in LLM Alignment","created":"2026-02-12","cited_by_count":1,"area":"alignment"},{"id":"2604.22045","title":"H-Sets: Hessian-Guided Discovery of Set-Level Feature Interactions in Image Classifiers","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2201.12835","title":"Debiased-CAM to mitigate systematic error with faithful visual explanations of machine learning","created":"2022-01-30","cited_by_count":0,"area":null},{"id":"2212.06151","title":"Utilizing Mutations to Evaluate Interpretability of Neural Networks on Genomic Data","created":"2022-12-12","cited_by_count":0,"area":null},{"id":"2403.06013","title":"Are Classification Robustness and Explanation Robustness Really Strongly Correlated? An Analysis Through Input Loss Landscape","created":"2024-03-09","cited_by_count":0,"area":null},{"id":"2405.01849","title":"Stability of Explainable Recommendation","created":"2024-05-03","cited_by_count":0,"area":null},{"id":"2405.01963","title":"From Attack to Defense: Insights into Deep Learning Security Measures in Black-Box Settings","created":"2024-05-03","cited_by_count":0,"area":null},{"id":"2504.17471","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","created":"2025-04-24","cited_by_count":0,"area":null},{"id":"2505.12421","title":"Fixed Point Explainability","created":"2025-05-18","cited_by_count":0,"area":null},{"id":"2507.14248","title":"Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack","created":"2025-07-18","cited_by_count":0,"area":null},{"id":"2509.03056","title":"Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs","created":"2025-09-03","cited_by_count":0,"area":null},{"id":"2511.12956","title":"T2I-Based Physical-World Appearance Attack against Traffic Sign Recognition Systems in Autonomous Driving","created":"2025-11-17","cited_by_count":0,"area":null},{"id":"2512.06665","title":"Rethinking Robustness: A New Approach to Evaluating Feature Attribution Methods","created":"2025-12-07","cited_by_count":0,"area":null},{"id":"2602.02763","title":"Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2603.07302","title":"Training for Trustworthy Saliency Maps: Adversarial Training Meets Feature-Map Smoothing","created":"2026-03-07","cited_by_count":0,"area":null},{"id":"2608.14130","title":"AlignFace: Human-Aligned Face Similarity Metric with Interpretable Concept Relations","created":"2026-08-14","cited_by_count":0,"area":null}],"next_cursor":null}