Related papers: DynaMark: A Reinforcement Learning Framework for D…

Training intelligent agents through reinforcement learning is a notoriously unstable procedure. Massive parallelization on GPUs and distributed systems has been exploited to generate a large amount of training experiences and consequently…

We introduce EfficientTDMPC, a sample-efficient model-based reinforcement learning method for continuous control built on the TD-MPC family of algorithms. Central to this family is a planner that aims to find an action sequence that…

Deep learning has emerged as a leading approach for Automatic Modulation Classification (AMC), demonstrating superior performance over traditional methods. However, vulnerability to adversarial attacks and susceptibility to data…

The growing complexity of cyber threats has rendered static firewalls increasingly ineffective for dynamic, real-time intrusion prevention. This paper proposes a novel AI-driven dynamic firewall optimization framework that leverages deep…

Model predictive control (MPC) is a powerful technique for solving dynamic control tasks. In this paper, we show that there exists a close connection between MPC and online learning, an abstract theoretical framework for analyzing online…

Heavy-duty hydraulic manipulators (HHMs) operate under strict physical and safety-critical constraints due to their large size, high power, and complex nonlinear dynamics. Ensuring that both joint-level and end-effector trajectories remain…

Model Predictive Control (MPC) is attracting tremendous attention in the autonomous driving task as a powerful control technique. The success of an MPC controller strongly depends on an accurate internal dynamics model. However, the static…

We propose a novel benchmark environment for Safe Reinforcement Learning focusing on aquatic navigation. Aquatic navigation is an extremely challenging task due to the non-stationary environment and the uncertainties of the robotic…

Large language models (LLMs) can be trained or fine-tuned on data obtained without the owner's consent. Verifying whether a specific LLM was trained on particular data instances or an entire dataset is extremely challenging. Dataset…

Watermarking is a commonly used strategy to protect creators' rights to digital images, videos and audio. Recently, watermarking methods have been extended to deep learning models -- in principle, the watermark should be preserved when an…

In this paper we describe a new conceptual framework that connects approximate Dynamic Programming (DP), Model Predictive Control (MPC), and Reinforcement Learning (RL). This framework centers around two algorithms, which are designed…

Watermarking is one of the most important copyright protection tools for digital media. The most challenging type of watermarking is the imperceptible one, which embeds identifying information in the data while retaining the latter's…

With the rapid advancement of speech generative models, unauthorized voice cloning poses significant privacy and security risks. Speech watermarking offers a viable solution for tracing sources and preventing misuse. Current watermarking…

Despite the tremendous success, deep neural networks are exposed to serious IP infringement risks. Given a target deep model, if the attacker knows its full information, it can be easily stolen by fine-tuning. Even if only its output is…

Watermarking plays a key role in the provenance and detection of AI-generated content. While existing methods prioritize robustness against real-world distortions (e.g., JPEG compression and noise addition), we reveal a fundamental…

Rapid advances in generative AI have led to increasingly realistic deepfakes, posing growing challenges for law enforcement and public trust. Existing passive deepfake detectors struggle to keep pace, largely due to their dependence on…

Deep learning-based image watermarking, while robust against conventional distortions, remains vulnerable to advanced adversarial and regeneration attacks. Conventional countermeasures, which jointly optimize the encoder and decoder via a…

A state-feedback watermarking signal design for the detection of replay attacks in linear systems is proposed. The control input is augmented with a random time-delayed term of the system state estimate, in order to secure the system…

As there are increasing needs of sharing data for machine learning, there is growing attention for the owners of the data to claim the ownership. Visible watermarking has been an effective way to claim the ownership of visual data, yet the…

This thesis develops data-driven machine learning algorithms to managing and optimizing the next-generation highly complex cyberphysical systems, which desperately need ground-breaking control, monitoring, and decision making schemes that…