Abstract is missing.
- Efficient and Effective Uncertainty Quantification in Gradient Boosting via Cyclical Gradient MCMCTian Tan, Carlos Huertas, Qi Zhao. [doi]
- Towards Multi-timescale Online Monitoring of AI ModelsFateh Kaakai, Paul-Marie Raffi. [doi]
- Safe Reinforcement Learning through Phasic Safety-Oriented Policy OptimizationSumanta Dey, Pallab Dasgupta, Soumyajit Dey. [doi]
- White-Box Adversarial Policies in Deep Reinforcement LearningStephen Casper, Dylan Hadfield-Menell, Gabriel Kreiman. [doi]
- Robustness with Black-Box Adversarial Attack using Reinforcement LearningSoumyendu Sarkar, Ashwin Ramesh Babu, Sajad Mousavi, Vineet Gundecha, Sahand Ghorbanpour, Alexander Shmakov, Ricardo Luna Gutierrez, Antonio Guillen, Avisek Naug. [doi]
- Domain-centric ADAS DatasetsVáclav Divis, Tobias Schuster, Marek Hrúz. [doi]
- Capabilities for Better ML EngineeringChenyang Yang 0002, Rachel A. Brower-Sinning, Grace A. Lewis, Christian Kästner, Tongshuang Wu. [doi]
- Bab: A novel algorithm for training clean model based on poisoned dataChen Chen, Haibo Hong, Mande Xie, Jun Shao, Tao Xiang. [doi]
- Towards Understanding How Self-training Tolerates Data Backdoor PoisoningSoumyadeep Pal, Ren Wang 0008, Yuguang Yao, Sijia Liu 0001. [doi]
- Towards a holistic approach for AI trustworthiness assessment based upon aids for multi-criteria aggregationJuliette Mattioli, Henri Sohier, Agnès Delaborde, Gabriel Pedroza, Kahina Amokrane-Ferka, Afef Awadid, Zakaria Chihani, Souhaiel Khalfaoui. [doi]
- Safety Assurance with Ensemble-based Uncertainty Estimation and overlapping alternative Predictions in Reinforcement LearningDirk Eilers, Simon Burton 0001, Felippe Schmoeller da Roza, Karsten Roscher. [doi]
- A Framework Quantifying Trustworthiness of Supervised Machine and Deep Learning ModelsAlberto Huertas Celdrán, Jan Kreischer, Melike Demirci, Joel Leupp, Pedro Miguel Sánchez Sánchez, Muriel Figueredo Franco, Gérôme Bovet, Gregorio Martínez Pérez, Burkhard Stiller. [doi]
- Formal Verification of Tree Ensembles against Real-World Composite Geometric PerturbationsValency Oscar Colaco, Simin Nadjm-Tehrani. [doi]
- Standardizing the Probabilistic Sources of Uncertainty for the sake of Safety Deep LearningAxel Brando, Isabel Serra, Enrico Mezzetti, Francisco J. Cazorla, Jaume Abella 0001. [doi]
- Critically Assessing the State of the Art in CPU-based Local Robustness VerificationMatthias König, Annelot Bosman, Holger H. Hoos, Jan N. van Rijn. [doi]
- Backdoor Attack Detection in Computer Vision by Applying Matrix Factorization on the Weights of Deep NetworksKhondoker Murad Hossain, Tim Oates 0001. [doi]
- On Evaluating Adversarial Robustness of Chest X-ray ClassificationSalah Ghamizi, Maxime Cordy, Mike Papadakis, Yves Le Traon. [doi]
- Less is More: Data Pruning for Faster Adversarial TrainingYize Li, Pu Zhao 0001, Xue Lin, Bhavya Kailkhura, Ryan A. Goldhahn. [doi]
- A Taxonomic System for Failure Cause Analysis of Open Source AI IncidentsNikiforos Pittaras, Sean McGregor. [doi]
- Out-of-Distribution Detection Using Deep Neural Network Latent Space UncertaintyFabio Arnez, Ansgar Radermacher, François Terrier. [doi]
- Towards Developing Safety Assurance Cases for Learning-Enabled Medical Cyber-Physical SystemsMaryam Bagheri 0001, Josephine Lamp, Xugui Zhou, Lu Feng 0001, Homa Alemzadeh. [doi]
- Evaluation of GAN Architectures for Adversarial Robustness of Convolution ClassifierWeimin Zhao, Sanaa A. Alwidian, Qusay H. Mahmoud. [doi]
- Towards Safety Assurance of Uncertainty-Aware Reinforcement Learning AgentsFelippe Schmoeller Roza, Simon Hadwiger, Ingo Thon, Karsten Roscher. [doi]
- Active Reward Learning from Multiple TeachersPeter Barnett, Rachel Freedman, Justin Svegliato, Stuart Russell 0001. [doi]
- REVEALE: Reward Verification and Learning Using ExplanationsSaaduddin Mahmud, Sandhya Saisubramanian, Shlomo Zilberstein. [doi]
- A Robust Drift Detection Algorithm with High Accuracy and Low False Positives RateMaxime Fuccellaro, Laurent Simon, Akka Zemmari. [doi]
- Transfer Assurance for Machine Learning in Autonomous SystemsChiara Picardi, Richard Hawkins, Colin Paterson, Ibrahim Habli. [doi]
- Personalized Models Resistant to Malicious Attacks for Human-centered Trusted AITeddy Ferdinan, Jan Kocon. [doi]