Related papers: A Unified Hardware-based Threat Detector for AI Ac…
Recently, web-based Large Language Model (LLM) agents autonomously perform increasingly complex tasks, thereby bringing significant convenience. However, they also amplify the risks of malicious misuse cases such as unauthorized collection…
Safety filtering is an effective method for enforcing constraints in safety-critical systems, but existing methods typically assume perfect state information. This limitation is especially problematic for systems that rely on neural network…
Federated Learning (FL) enables collaborative model training across distributed devices while preserving local data privacy, making it ideal for mobile and embedded systems. However, the decentralized nature of FL also opens vulnerabilities…
Covert channels (CCs) in wireless chips pose a serious security threat, as they enable the exfiltration of sensitive information from the chip to an external attacker. In this work, we propose an AI-based defense mechanism deployed at the…
Artificial Intelligence (AI) is widely adopted today for its ability to detect patterns, automate tasks, and reduce time and cost across various applications. Its integration into Cybersecurity has garnered significant attention,…
In this dissertation, we propose a memory and computing coordinated methodology to thoroughly exploit the characteristics and capabilities of the GPU-based heterogeneous system to effectively optimize applications' performance and privacy.…
End-point monitoring solutions are widely deployed in today's enterprise environments to support advanced attack detection and investigation. These monitors continuously record system-level activities as audit logs and provide deep…
Energy theft poses a significant threat to the stability and efficiency of smart grids, leading to substantial economic losses and operational challenges. Traditional centralized machine learning approaches for theft detection require…
Not too long ago, AI security used to mean the research and practice of how AI can empower cybersecurity, that is, AI for security. Ever since Ian Goodfellow and his team popularized adversarial attacks on machine learning, security for AI…
In recent years, neural backdoor attack has been considered to be a potential security threat to deep learning systems. Such systems, while achieving the state-of-the-art performance on clean data, perform abnormally on inputs with…
Since the first Graphical User Interface (GUI) prototype was invented in the 1970s, GUI systems have been deployed into various personal computer systems and server platforms. Recently, with the development of artificial intelligence (AI)…
Deep generative models have demonstrated impressive performance in various computer vision applications, including image synthesis, video generation, and medical analysis. Despite their significant advancements, these models may be used for…
Deep learning models are being integrated into a wide range of high-impact, security-critical systems, from self-driving cars to medical diagnosis. However, recent research has demonstrated that many of these deep learning architectures are…
We present BadGD, a unified theoretical framework that exposes the vulnerabilities of gradient descent algorithms through strategic backdoor attacks. Backdoor attacks involve embedding malicious triggers into a training dataset to disrupt…
The increasing deployment of Machine Learning (ML) models in sensitive domains motivates the need for robust, practical privacy assessment tools. PrivacyGuard is a comprehensive tool for empirical differential privacy (DP) analysis,…
Deep learning models achieve excellent performance in numerous machine learning tasks. Yet, they suffer from security-related issues such as adversarial examples and poisoning (backdoor) attacks. A deep learning model may be poisoned by…
Trusted execution environments in several existing and upcoming CPUs demonstrate the success of confidential computing, with the caveat that tenants cannot securely use accelerators such as GPUs and FPGAs. In this paper, we reconsider the…
Diffusion models are vulnerable to backdoor attacks, where malicious attackers inject backdoors by poisoning certain training samples during the training stage. This poses a significant threat to real-world applications in the…
As the demands for railway transportation safety increase, traditional methods of rail track inspection no longer meet the needs of modern railway systems. To address the issues of automation and efficiency in rail fault detection, this…
6G -- sixth generation -- is the latest cellular technology currently under development for wireless communication systems. In recent years, machine learning algorithms have been applied widely in various fields, such as healthcare,…