Related papers: Stealing AI Model Weights Through Covert Communica…

AI systems are rapidly advancing in capability, and frontier model developers broadly acknowledge the need for safeguards against serious misuse. However, this paper demonstrates that fine-tuning, whether via open weights or closed…

Recent advancements in Artificial Intelligence namely in Deep Learning has heightened its adoption in many applications. Some are playing important roles to the extent that we are heavily dependent on them for our livelihood. However, as…

The increased adoption of Artificial Intelligence (AI) presents an opportunity to solve many socio-economic and environmental challenges; however, this cannot happen without securing AI-enabled technologies. In recent years, most AI models…

Model stealing attacks endanger the confidentiality of machine learning models offered as a service. Although these models are kept secret, a malicious party can query a model to label data samples and train their own substitute model,…

Adversarial attacks on deep learning-based models pose a significant threat to the current AI infrastructure. Among them, Trojan attacks are the hardest to defend against. In this paper, we first introduce a variation of the Badnet kind of…

Deep neural networks (DNNs) have become the essential components for various commercialized machine learning services, such as Machine Learning as a Service (MLaaS). Recent studies show that machine learning services face severe privacy…

This paper examines the challenges in distributing AI models through model zoos and file transfer mechanisms. Despite advancements in security measures, vulnerabilities persist, necessitating a multi-layered approach to mitigate risks…

Generative adversarial networks (GANs) have shown remarkable success in image synthesis, making GAN models themselves commercially valuable to legitimate model owners. Therefore, it is critical to technically protect the intellectual…

Covert wireless communications are critical for concealing the existence of any transmission from adversarial wardens, particularly in complex environments with multiple heterogeneous detectors. This paper proposes a novel adversarial AI…

The dependability of AI models relies largely on the reliability of the underlying computation hardware. Hardware aging attacks can compromise the computing substrate and disrupt AI models over the long run. In this work, we present a new…

Ensuring end-to-end cross-layer communication security in military networks by selecting covert schemes between nodes is a key solution for military communication security. With the development of communication technology, covert…

We present a Trojan (backdoor or trapdoor) attack that targets deep learning applications in wireless communications. A deep learning classifier is considered to classify wireless signals using raw (I/Q) samples as features and modulation…

Data attacks on meter measurements in the power grid can lead to errors in state estimation. This paper presents a new data attack model where an adversary produces changes in state estimation despite failing bad-data detection checks. The…

Collaborative inference among multiple wireless edge devices has the potential to significantly enhance Artificial Intelligence (AI) applications, particularly for sensing and computer vision. This approach typically involves a three-stage…

Practitioners commonly download pretrained machine learning models from open repositories and finetune them to fit specific applications. We show that this practice introduces a new risk of privacy backdoors. By tampering with a pretrained…

This article presents a novel method for establishing an information theoretically secure encryption key over wireless channels. It exploits the fact that data transmission over wireless links is accompanied by packet error, while noise…

Artificial Intelligence has made a significant contribution to autonomous vehicles, from object detection to path planning. However, AI models require a large amount of sensitive training data and are usually computationally intensive to…

Obtaining a well-trained model involves expensive data collection and training procedures, therefore the model is a valuable intellectual property. Recent studies revealed that adversaries can `steal' deployed models even when they have no…

The Intelligence Advanced Research Projects Activity (IARPA) launched the TrojAI program to confront an emerging vulnerability in modern artificial intelligence: the threat of AI Trojans. These AI trojans are malicious, hidden backdoors…

We introduce the first model-stealing attack that extracts precise, nontrivial information from black-box production language models like OpenAI's ChatGPT or Google's PaLM-2. Specifically, our attack recovers the embedding projection layer…