Accepted Papers

Best Paper

Will be determined out of all papers (long and short orals) during the workshop.


Long Oral + Poster


ID 8: Reliable Trajectory Prediction and Uncertainty Quantification with Conditioned Diffusion Models (Poster ID: 82)


ID 11: Hinge-Wasserstein: Estimating Multimodal Aleatoric Uncertainty in Regression Tasks (Poster ID: 83)


ID 17: Towards 100x faster Randomized Smoothing: exploring the trade-off between sample budget and Certified Radius (Poster ID: 84)


ID 21: The Penalized Inverse Probability Measure for Conformal Classification (Poster ID: 92)



ID 22: Run-time Monitoring of 3D Object Detection in Automated Driving Systems Using Early Layer Neural Activation Patterns (Poster ID: 86)


Short Oral + Poster 


ID 2: Look, Listen, and Attack: Backdoor Attacks Against Video Action Recognition (Poster ID: 87)


ID 5: Understanding ReLU Network Robustness Through Test Set Certification Performance (Poster ID: 88)



ID 12: AdvDenoise: Fast Generation Framework of Universal and Robust Adversarial Patches Using Denoise (Poster ID: 89)



ID 14: Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations (Poster ID: 90)



ID 20: Situation Monitor: Zero-Shot Out-of-Distribution Detection based on Diversity based Budding Ensemble Architecture for Object Detection (Poster ID: 91)



ID 25: Reactive Model Correction: Mitigating Harm to Task-Relevant Features via Conditional Bias Suppression (Poster ID: 85)


ID 26: Investigating Calibration and Corruption Robustness of Post-hoc Pruned Perception CNNs: An Image Classification Benchmark Study (Poster ID: 93)


ID 27: Towards Weakly-Supervised Domain Adaptation for Lane Detection (Poster ID: 94)


ID 29: Towards Engineered Safe AI with Modular Concept Models (Poster ID: 95)



ID 30: Conformal Semantic Image Segmentation: Post-hoc quantification of predictive uncertainty (Poster ID: 96)



ID 31: A Comprehensive Analysis of Factors Impacting Membership Inference (Poster ID: 97)


ID 35: Exploiting CLIP Self-Consistency to Automate Image Augmentation for Safety Critical Scenarios (Poster ID: 98)


Camera Ready Instructions


Please find Camera-Ready Submission Instructions under the following link: https://clousi.hs-mannheim.de/index.php/s/m4s59WD43TGK3Fg

Additionally, you can find Author Submission Site Instructions here: https://clousi.hs-mannheim.de/index.php/s/ECJPYBpPcomAYMr