Related papers: Learning Password Best Practices Through In-Task I…

Text-based passwords continue to be the prime form of authentication to computer systems. Today, they are increasingly created and used with mobile text entry methods, such as touchscreens and mobile keyboards, in addition to traditional…

Membership Inference Attacks have emerged as a dominant method for empirically measuring privacy leakage from machine learning models. Here, privacy is measured by the {\em{advantage}} or gap between a score or a function computed on the…

The frequency with which people interact with technology means that users may develop interface habits, i.e. fast, automatic responses to stable interface cues. Design guidelines often assume that interface habits are beneficial. However,…

Deploying machine learning models in production may allow adversaries to infer sensitive information about training data. There is a vast literature analyzing different types of inference risks, ranging from membership inference to…

Ensuring privacy during inference stage is crucial to prevent malicious third parties from reconstructing users' private inputs from outputs of public models. Despite a large body of literature on privacy preserving learning (which ensures…

In this work, we ask for and answer what makes classical temporal-difference reinforcement learning with epsilon-greedy strategies cooperative. Cooperating in social dilemma situations is vital for animals, humans, and machines. While…

Recent years have witnessed many successful trials in the robot learning field. For contact-rich robotic tasks, it is challenging to learn coordinated motor skills by reinforcement learning. Imitation learning solves this problem by using a…

In the physical world, people have dynamic preferences, e.g., the same situation can lead to satisfaction for some humans and to frustration for others. Personalization is called for. The same observation holds for online behavior with…

There is a conflict between the need for security compliance by users and the fact that commonly they cannot afford to dedicate much of their time and energy to that security. A balanced level of user engagement in security is difficult to…

In this paper, we report on three experiments we have carried out in the context of the EMPATHY project, with the aim of helping users make better configuration choices in a smart home environment, and discuss our results. We found that…

Instruction-following language models are trained to be helpful and safe, yet their safety behavior can deteriorate under benign fine-tuning and worsen under adversarial updates. Existing defenses often offer limited protection or force a…

Safety is a crucial property of every robotic platform: any control policy should always comply with actuator limits and avoid collisions with the environment and humans. In reinforcement learning, safety is even more fundamental for…

As generative AI (GenAI) tools are increasingly used as informal tutors for mathematics learning, future systems may become more proactive and process-aware in deciding when and how to offer support. Yet such support raises an important…

Machine learning techniques are increasingly used for high-stakes decision-making, such as college admissions, loan attribution or recidivism prediction. Thus, it is crucial to ensure that the models learnt can be audited or understood by…

Socially aware robot navigation, where a robot is required to optimize its trajectory to maintain comfortable and compliant spatial interactions with humans in addition to reaching its goal without collisions, is a fundamental yet…

We develop a novel framework of bounded rationality under cognitive frictions that studies learning over optimal behavior through both deliberative reasoning and accumulated experiences. Using both types of information, agents engage in…

We develop a learning-based control algorithm for unknown dynamical systems under very severe data limitations. Specifically, the algorithm has access to streaming and noisy data only from a single and ongoing trial. It accomplishes such…

Recently, privacy issues in web services that rely on users' personal data have raised great attention. Unlike existing privacy-preserving technologies such as federated learning and differential privacy, we explore another way to mitigate…

While learning-based control techniques often outperform classical controller designs, safety requirements limit the acceptance of such methods in many applications. Recent developments address this issue through so-called predictive safety…

Regardless of the particular task we want them to perform in an environment, there are often shared safety constraints we want our agents to respect. For example, regardless of whether it is making a sandwich or clearing the table, a…