6 papers
Robust Adversarial Quantification via Conflict-Aware Evidential Deep Learning
Charmaine Barker, Daniel Bethell, Simos Gerasimou
Reliability of deep learning models is critical for deployment in high-stakes applications, where out-of-distribution or adversarial inputs may lead to detrimental outcomes. Eviden…
Safe But Not Sorry: Reducing Over-Conservatism in Safety Critics via Uncertainty-Aware Modulation
Daniel Bethell, Simos Gerasimou, Radu Calinescu +1
Ensuring the safe exploration of reinforcement learning (RL) agents is critical for deployment in real-world systems. Yet existing approaches struggle to strike the right balance:…
Learning to Navigate Under Imperfect Perception: Conformalised Segmentation for Safe Reinforcement Learning
Daniel Bethell, Simos Gerasimou, Radu Calinescu +1
Reliable navigation in safety-critical environments requires both accurate hazard perception and principled uncertainty handling to strengthen downstream safety handling. Despite t…
Learning Fairer Representations with FairVIC
Charmaine Barker, Daniel Bethell, Dimitar Kazakov
Mitigating bias in automated decision-making systems, particularly in deep learning models, is a critical challenge due to nuanced definitions of fairness, dataset-specific biases,…
Guided Uncertainty Learning Using a Post-Hoc Evidential Meta-Model
Charmaine Barker, Daniel Bethell, Simos Gerasimou
Reliable uncertainty quantification remains a major obstacle to the deployment of deep learning models under distributional shift. Existing post-hoc approaches that retrofit pretra…
Safe Reinforcement Learning in Black-Box Environments via Adaptive Shielding
Daniel Bethell, Simos Gerasimou, Radu Calinescu +1
Empowering safe exploration of reinforcement learning (RL) agents during training is a critical challenge towards their deployment in many real-world scenarios. When prior knowledg…