[HTML][HTML] A survey of safety and trustworthiness of large language models through the lens of verification and validation
Large language models (LLMs) have exploded a new heatwave of AI for their ability to
engage end-users in human-level conversations with detailed and articulate answers across …
engage end-users in human-level conversations with detailed and articulate answers across …
Certified policy smoothing for cooperative multi-agent reinforcement learning
Cooperative multi-agent reinforcement learning (c-MARL) is widely applied in safety-critical
scenarios, thus the analysis of robustness for c-MARL models is profoundly important …
scenarios, thus the analysis of robustness for c-MARL models is profoundly important …
Reward Certification for Policy Smoothed Reinforcement Learning
Reinforcement Learning (RL) has achieved remarkable success in safety-critical areas, but it
can be weakened by adversarial attacks. Recent studies have introduced``smoothed …
can be weakened by adversarial attacks. Recent studies have introduced``smoothed …
[HTML][HTML] Bridging formal methods and machine learning with model checking and global optimisation
Formal methods and machine learning are two research fields with drastically different
foundations and philosophies. Formal methods utilise mathematically rigorous techniques …
foundations and philosophies. Formal methods utilise mathematically rigorous techniques …
Enhancing robustness in video recognition models: Sparse adversarial attacks and beyond
Recent years have witnessed increasing interest in adversarial attacks on images, while
adversarial video attacks have seldom been explored. In this paper, we propose a sparse …
adversarial video attacks have seldom been explored. In this paper, we propose a sparse …
Model-agnostic reachability analysis on deep neural networks
Verification plays an essential role in the formal analysis of safety-critical systems. Most
current verification methods have specific requirements when working on Deep Neural …
current verification methods have specific requirements when working on Deep Neural …
DIRECT Optimisation with Bayesian Insights: Assessing Reliability Under Fixed Computational Budgets
We introduce a method for probabilistically evaluating the reliability of Lipschitzian global
optimisation under a constrained computational budget, a context frequently encountered in …
optimisation under a constrained computational budget, a context frequently encountered in …