相关论文: Stealing AI Model Weights Through Covert Communica…

Similar to the revolution of open source code sharing, Artificial Intelligence (AI) model sharing is gaining increased popularity. However, the fast adaptation in the industry, lack of awareness, and ability to exploit the models make them…

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…

AI-based sensing at wireless edge devices has the potential to significantly enhance Artificial Intelligence (AI) applications, particularly for vision and perception tasks such as in autonomous driving and environmental monitoring. AI…

Model extraction increasingly attracts research attentions as keeping commercial AI models private can retain a competitive advantage. In some scenarios, AI models are trained proprietarily, where neither pre-trained models nor sufficient…

We develop and study new adversarial perturbations that enable an attacker to gain control over decisions in generic Artificial Intelligence (AI) systems including deep learning neural networks. In contrast to adversarial data modification,…

Hardware Trojans can inflict harm on wireless networks by exploiting the link margins inherent in communication systems. We investigate a setting in which, alongside a legitimate communication link, a hardware Trojan embedded in the…

Recent advancements of Deep Neural Networks (DNNs) have seen widespread deployment in multiple security-sensitive domains. The need of resource-intensive training and use of valuable domain-specific training data have made these models a…

As frontier AIs become more powerful and costly to develop, adversaries have increasing incentives to steal model weights by mounting exfiltration attacks. In this work, we consider exfiltration attacks where an adversary attempts to sneak…

We consider an echo-assisted communication model wherein block-coded messages, when transmitted across several frames, reach the destination as multiple noisy copies. We address adversarial attacks on such models wherein a subset of the…

Backdoor attacks represent a subtle yet effective class of cyberattacks targeting AI models, primarily due to their stealthy nature. The model behaves normally on clean data but exhibits malicious behavior only when the attacker embeds a…

Model stealing attacks have become a serious concern for deep learning models, where an attacker can steal a trained model by querying its black-box API. This can lead to intellectual property theft and other security and privacy risks. The…

The flexibility and complexity of IPv6 extension headers allow attackers to create covert channels or bypass security mechanisms, leading to potential data breaches or system compromises. The mature development of machine learning has…

Building advanced machine learning (ML) models requires expert knowledge and many trials to discover the best architecture and hyperparameter settings. Previous work demonstrates that model information can be leveraged to assist other…

Covert channel networks are a well-known method for circumventing the security measures organizations put in place to protect their networks from adversarial attacks. This paper introduces a novel method based on bit-rate modulation for…

As training artificial intelligence (AI) models is a lengthy and hence costly process, leakage of such a model's internal parameters is highly undesirable. In the case of AI accelerators, side-channel information leakage opens up the threat…

Model extraction emerges as a critical security threat with attack vectors exploiting both algorithmic and implementation-based approaches. The main goal of an attacker is to steal as much information as possible about a protected victim…

Federated Learning (FL) enables multiple clients, such as mobile phones and IoT devices, to collaboratively train a global machine learning model while keeping their data localized. However, recent studies have revealed that the training…

The need for secure and private Artificial Intelligence (AI) and Machine Learning (ML) on edge and mobile devices has increased the necessity of protecting the architecture of these systems from threats to both security and privacy. With an…

Machine learning models were shown to be vulnerable to model stealing attacks, which lead to intellectual property infringement. Among other methods, substitute model training is an all-encompassing attack applicable to any machine learning…

Numerous safety- or security-critical systems depend on cameras to perceive their surroundings, further allowing artificial intelligence (AI) to analyze the captured images to make important decisions. However, a concerning attack vector…