Related papers: Position: No Retroactive Cure for Infringement dur…

The growing enforcement of the right to be forgotten regulations has propelled recent advances in certified (graph) unlearning strategies to comply with data removal requests from deployed machine learning (ML) models. Motivated by the…

AI model alignment is crucial due to inadvertent biases in training data and the underspecified machine learning pipeline, where models with excellent test metrics may not meet end-user requirements. While post-training alignment via human…

In the context of hardware trust and assurance, reverse engineering has been often considered as an illegal action. Generally speaking, reverse engineering aims to retrieve information from a product, i.e., integrated circuits (ICs) and…

Naively trained Deep Reinforcement Learning agents may fail to satisfy vital safety constraints. To avoid costly retraining, we may desire to repair a previously trained reinforcement learning agent to obviate unsafe behaviour. We devise a…

Ante-hoc interpretability methods based on prototypes provide highly accurate explanations by utilizing the intuitive "this looks like that" reasoning paradigm. On the other hand, post-hoc models can explain predictions for a single image…

The pursuit of fairness in machine learning (ML), ensuring that the models do not exhibit biases toward protected demographic groups, typically results in a compromise scenario. This compromise can be explained by a Pareto frontier where…

Ensuring that online discussions are civil and productive is a major challenge for social media platforms. Such platforms usually rely both on users and on automated detection tools to flag inappropriate arguments of other users, which…

Although deep reinforcement learning has become a promising machine learning approach for sequential decision-making problems, it is still not mature enough for high-stake domains such as autonomous driving or medical applications. In such…

Exact unlearning was first introduced as a privacy mechanism that allowed a user to retract their data from machine learning models on request. Shortly after, inexact schemes were proposed to mitigate the impractical costs associated with…

Generating calibrated and sharp neural network predictive distributions for regression problems is essential for optimal decision-making in many real-world applications. To address the miscalibration issue of neural networks, various…

The rapid proliferation of artificial intelligence (AI) has exposed significant deficiencies in risk governance. While ex-ante harm identification and prevention have advanced, Responsible AI scholarship remains underdeveloped in addressing…

Even as we engineer LLMs for alignment and safety, they often uncover biases from pre-training data's statistical regularities (from disproportionate co-occurrences to stereotypical associations mirroring human cognitive biases). This leads…

Addressing the large inefficiencies generated by the Deferred Acceptance (DA) mechanism requires priority violations, but which ones are justifiable? The leading approach is to ask individuals if they consent to waive their priority…

Collaborative machine learning settings like federated learning can be susceptible to adversarial interference and attacks. One class of such attacks is termed model inversion attacks, characterised by the adversary reverse-engineering the…

Pre-trained Large Language Models (LLMs) have demonstrated remarkable capabilities but also pose risks by learning and generating copyrighted material, leading to significant legal and ethical concerns. In a potential real-world scenario,…

We study reinforcement learning (RL) on volatility surfaces through the lens of Scientific AI. We ask whether axiomatic no-arbitrage laws, imposed as soft penalties on a learned world model, can reliably align high-capacity RL agents, or…

Machine learning is data hungry; the more data a model has access to in training, the more likely it is to perform well at inference time. Distinct parties may want to combine their local data to gain the benefits of a model trained on a…

Machine unlearning is rapidly becoming a practical requirement, driven by privacy regulations, data errors, and the need to remove harmful or corrupted training samples. Despite this, most existing methods tackle the problem purely from a…

Post-training improves large language models (LLMs) but often worsens confidence calibration, leading to systematic overconfidence. Recent unsupervised post-hoc methods for post-trained LMs (PoLMs) mitigate this by aligning PoLM confidence…

Since the early days of the Explainable AI movement, post-hoc explanations have been praised for their potential to improve user understanding, promote trust, and reduce patient safety risks in black box medical AI systems. Recently,…