相关论文: Dynamic Watermarking for General LTI Systems

Watermarking has become one of promising techniques to not only aid in identifying AI-generated images but also serve as a deterrent against the unethical use of these models. However, the robustness of watermarking techniques has not been…

The growing number of cyber-attacks against Industrial Control Systems (ICS) in recent years has elevated security concerns due to the potential catastrophic impact. Considering the complex nature of ICS, detecting a cyber-attack in them is…

The wide deployment of Face Recognition (FR) systems poses privacy risks. One countermeasure is adversarial attack, deceiving unauthorized malicious FR, but it also disrupts regular identity verification of trusted authorizers, exacerbating…

Latent Diffusion Models (LDMs) enable a wide range of applications but raise ethical concerns regarding illegal utilization. Adding watermarks to generative model outputs is a vital technique employed for copyright tracking and mitigating…

Cyber attacks targeting Industrial Control Systems (ICS) have become increasingly sophisticated and hard to identify. Detecting such attacks requires integrating low-level behavioral cues with high-level semantic interpretation, a…

Cyber-physical systems integrate computation, communication, and physical capabilities to interact with the physical world and humans. Besides failures of components, cyber-physical systems are prone to malicious attacks so that specific…

Watermark algorithms for large language models (LLMs) have achieved extremely high accuracy in detecting text generated by LLMs. Such algorithms typically involve adding extra watermark logits to the LLM's logits at each generation step.…

Deep neural networks are vulnerable to malicious fine-tuning attacks such as data poisoning and backdoor attacks. Therefore, in recent research, it is proposed how to detect malicious fine-tuning of neural network models. However, it…

Stealthy false data injection attacks on cyber-physical systems introduce erroneous measurements onto sensors with the intent to degrade system performance. An intelligent attacker can design stealthy attacks with knowledge of the system…

The advancement of artificial intelligence generated content (AIGC) has created a pressing need for robust image watermarking that can withstand both conventional signal processing and novel semantic editing attacks. Current deep…

This paper considers the problem of designing physical watermark signals in order to optimally detect possible replay attack in a linear time-invariant system, under the assumption that the system parameters are unknown and need to be…

We address the problem of estimating the state of a differentially flat system from measurements that may be corrupted by an adversarial attack. In cyber-physical systems, malicious attacks can directly compromise the system's sensors or…

Modern smart home control systems utilize real-time occupancy and activity monitoring to ensure control efficiency, occupants' comfort, and optimal energy consumption. Moreover, adopting machine learning-based anomaly detection models…

Atmospheric fronts are associated with precipitation and strong diabatic processes. Therefore, detecting fronts objectively from reanalyses is a prerequisite for the long-term study of their weather impacts. For this purpose, several…

Watermarking acts as a critical safeguard in text generated by Large Language Models (LLMs). By embedding identifiable signals into model outputs, watermarking enables reliable attribution and enhances the security of machine-generated…

The subspace identification method (SIM) has been extensively employed in the identification of discrete-time multiple-input multiple-output (MIMO) linear time-invariant (LTI) systems. This paper focuses on the analysis of perturbation…

Recent fine-tuning techniques for diffusion models enable them to reproduce specific image sets, such as particular faces or artistic styles, but also introduce copyright and security risks. Dataset watermarking has been proposed to ensure…

The most effective techniques to detect LLM-generated text rely on inserting a detectable signature -- or watermark -- during the model's decoding process. Most existing watermarking methods require access to the underlying LLM's logits,…

Machine learning models are being used in an increasing number of critical applications; thus, securing their integrity and ownership is critical. Recent studies observed that adversarial training and watermarking have a conflicting…

Machine learning is increasingly used in security-critical applications, such as autonomous driving, face recognition and malware detection. Most learning methods, however, have not been designed with security in mind and thus are…