Related papers: Policy Poisoning in Batch Learning for Linear Quad…

Humans have come to rely on machines for reducing excessive information to manageable representations. But this reliance can be abused -- strategic machines might craft representations that manipulate their users. How can a user make good…

The concept of learned index structures relies on the idea that the input-output functionality of a database index can be viewed as a prediction task and, thus, be implemented using a machine learning model instead of traditional…

In offline multi-agent reinforcement learning (MARL), agents estimate policies from a given dataset. We study reward-poisoning attacks in this setting where an exogenous attacker modifies the rewards in the dataset before the agents see the…

Distillation-based federated learning has emerged as a promising collaborative learning approach, where clients share the output logit vectors of a public dataset rather than their private model parameters. This practice reduces the risk of…

In this paper, we consider the problem of multi-agent navigation in partially observable grid environments. This problem is challenging for centralized planning approaches as they, typically, rely on the full knowledge of the environment.…

Reinforcement learning is a promising approach to learning control policies for performing complex multi-agent robotics tasks. However, a policy learned in simulation often fails to guarantee even simple safety properties such as obstacle…

The lifecycle of large language models (LLMs) is far more complex than that of traditional machine learning models, involving multiple training stages, diverse data sources, and varied inference methods. While prior research on data…

We consider optimal control of an unknown multi-agent linear quadratic (LQ) system where the dynamics and the cost are coupled across the agents through the mean-field (i.e., empirical mean) of the states and controls. Directly using…

Machine learning models have achieved great success in supervised learning tasks for end-to-end training, which requires a large amount of labeled data that is not always feasible. Recently, many practitioners have shifted to…

Property inference attacks consider an adversary who has access to the trained model and tries to extract some global statistics of the training data. In this work, we study property inference in scenarios where the adversary can…

Deep neural networks are vulnerable to backdoor attacks, a type of adversarial attack that poisons the training data to manipulate the behavior of models trained on such data. Clean-label attacks are a more stealthy form of backdoor attacks…

Distributed optimal control is known to be challenging and can become intractable even for linear-quadratic regulator problems. In this work, we study a special class of such problems where distributed state feedback controllers can give…

Large language models are increasingly augmented with persistent memory, allowing assistants to store user-specific information across sessions for personalization and continuity. This statefulness introduces a new security risk:…

Reinforcement learning algorithms typically necessitate extensive exploration of the state space to find optimal policies. However, in safety-critical applications, the risks associated with such exploration can lead to catastrophic…

Prompt injection attack, where an attacker injects a prompt into the original one, aiming to make an Large Language Model (LLM) follow the injected prompt to perform an attacker-chosen task, represent a critical security threat. Existing…

We study the problem of model selection in batch policy optimization: given a fixed, partial-feedback dataset and $M$ model classes, learn a policy with performance that is competitive with the policy derived from the best model class. We…

In the evolving landscape of Federated Learning (FL), a new type of attacks concerns the research community, namely Data Poisoning Attacks, which threaten the model integrity by maliciously altering training data. This paper introduces a…

Machine learning models have been widely adopted in several fields. However, most recent studies have shown several vulnerabilities from attacks with a potential to jeopardize the integrity of the model, presenting a new window of research…

Behavioral cloning, or more broadly, learning from demonstrations (LfD) is a priomising direction for robot policy learning in complex scenarios. Albeit being straightforward to implement and data-efficient, behavioral cloning has its own…

This paper studies the learning-to-control problem under process and sensing uncertainties for dynamical systems. In our previous work, we developed a data-based generalization of the iterative linear quadratic regulator (iLQR) to design…