Zhengping Luo

Zhengping Jay Luo, Tyler Stewart, Mourya Narasareddygari et al.

Quantum computing has garnered significant attention in recent years from both academia and industry due to its potential to achieve a "quantum advantage" over classical computers. The advent of quantum computing introduces new challenges for security and privacy. This poster explores the performance and security implications of quantum computing through a case study of machine learning in a real-world application. We compare the performance of quantum machine learning (QML) algorithms to their classical counterparts using the Alzheimer's disease dataset. Our results indicate that QML algorithms show promising potential while they still have not surpassed classical algorithms in terms of learning capability and convergence difficulty, and running quantum algorithms through simulations on classical computers requires significantly large memory space and CPU time. Our study also indicates that QMLs have inherited vulnerabilities from classical machine learning algorithms while also introduce new attack vectors.

Binhao Ma, Hanqing Guo, Zhengping Jay Luo et al.

Recent advances in Multimodal Large Language Models (MLLMs) have significantly enhanced the naturalness and flexibility of human computer interaction by enabling seamless understanding across text, vision, and audio modalities. Among these, voice enabled models such as SpeechGPT have demonstrated considerable improvements in usability, offering expressive, and emotionally responsive interactions that foster deeper connections in real world communication scenarios. However, the use of voice introduces new security risks, as attackers can exploit the unique characteristics of spoken language, such as timing, pronunciation variability, and speech to text translation, to craft inputs that bypass defenses in ways not seen in text-based systems. Despite substantial research on text based jailbreaks, the voice modality remains largely underexplored in terms of both attack strategies and defense mechanisms. In this work, we present an adversarial attack targeting the speech input of aligned MLLMs in a white box scenario. Specifically, we introduce a novel token level attack that leverages access to the model's speech tokenization to generate adversarial token sequences. These sequences are then synthesized into audio prompts, which effectively bypass alignment safeguards and to induce prohibited outputs. Evaluated on SpeechGPT, our approach achieves up to 89 percent attack success rate across multiple restricted tasks, significantly outperforming existing voice based jailbreak methods. Our findings shed light on the vulnerabilities of voice-enabled multimodal systems and to help guide the development of more robust next-generation MLLMs.

Zhengping Luo, Shangqing Zhao, Zhuo Lu et al.

As Internet of Things (IoT) has emerged as the next logical stage of the Internet, it has become imperative to understand the vulnerabilities of the IoT systems when supporting diverse applications. Because machine learning has been applied in many IoT systems, the security implications of machine learning need to be studied following an adversarial machine learning approach. In this paper, we propose an adversarial machine learning based partial-model attack in the data fusion/aggregation process of IoT by only controlling a small part of the sensing devices. Our numerical results demonstrate the feasibility of this attack to disrupt the decision making in data fusion with limited control of IoT devices, e.g., the attack success rate reaches 83\% when the adversary tampers with only 8 out of 20 IoT devices. These results show that the machine learning engine of IoT system is highly vulnerable to attacks even when the adversary manipulates a small portion of IoT devices, and the outcome of these attacks severely disrupts IoT system operations.

Zhengping Luo, Shangqing Zhao, Zhuo Lu et al.

Defense strategies have been well studied to combat Byzantine attacks that aim to disrupt cooperative spectrum sensing by sending falsified versions of spectrum sensing data to a fusion center. However, existing studies usually assume network or attackers as passive entities, e.g., assuming the prior knowledge of attacks is known or fixed. In practice, attackers can actively adopt arbitrary behaviors and avoid pre-assumed patterns or assumptions used by defense strategies. In this paper, we revisit this security vulnerability as an adversarial machine learning problem and propose a novel learning-empowered attack framework named Learning-Evaluation-Beating (LEB) to mislead the fusion center. Based on the black-box nature of the fusion center in cooperative spectrum sensing, our new perspective is to make the adversarial use of machine learning to construct a surrogate model of the fusion center's decision model. We propose a generic algorithm to create malicious sensing data using this surrogate model. Our real-world experiments show that the LEB attack is effective to beat a wide range of existing defense strategies with an up to 82% of success ratio. Given the gap between the proposed LEB attack and existing defenses, we introduce a non-invasive method named as influence-limiting defense, which can coexist with existing defenses to defend against LEB attack or other similar attacks. We show that this defense is highly effective and reduces the overall disruption ratio of LEB attack by up to 80%.