Related papers: DynaMO: Protecting Mobile DL Models through Coupli…

A transfer function approach has recently proven effective for calibrating deep learning (DL) algorithms in quantitative ultrasound (QUS), addressing data shifts at both the acquisition and machine levels. Expanding on this approach, we…

Numerous security threats are emerging from untrusted players in the integrated circuit (IC) ecosystem. Among them, reverse engineering practices with the intent to counterfeit, overproduce, or modify an IC are worrying. In recent years,…

Diffusion models (DMs) have achieved state-of-the-art performance on various generative tasks such as image synthesis, text-to-image, and text-guided image-to-image generation. However, the more powerful the DMs, the more harmful they…

In this paper, we introduce Dynamic Layer Operations (DLO), a novel approach for vertically scaling transformer-based Large Language Models (LLMs) by dynamically expanding, activating, or skipping layers using a sophisticated routing policy…

Jailbreak attacks pose persistent threats to large language models (LLMs). Current safety alignment methods have attempted to address these issues, but they experience two significant limitations: insufficient safety alignment depth and…

Moving Target Defense and Cyber Deception emerged in recent years as two key proactive cyber defense approaches, contrasting with the static nature of the traditional reactive cyber defense. The key insight behind these approaches is to…

Model extraction is a severe threat to Machine Learning-as-a-Service systems, especially through data-free approaches, where dishonest users can replicate the functionality of a black-box target model without access to realistic data.…

Incorporating deep learning (DL) into multiple-input multiple-output (MIMO) detection has been deemed as a promising technique for future wireless communications. However, most DL-based detection algorithms are lack of theoretical…

Mobile applications continuously generate DNS queries that can reveal sensitive user behavioral patterns even when communications are encrypted. This paper presents a privacy enhancement framework based on query forgery to protect users…

Self-supervised models are increasingly prevalent in machine learning (ML) since they reduce the need for expensively labeled data. Because of their versatility in downstream applications, they are increasingly used as a service exposed via…

Currently, deep neural networks (DNNs) are widely adopted in different applications. Despite its commercial values, training a well-performing DNN is resource-consuming. Accordingly, the well-trained model is valuable intellectual property…

High-performance Deep Neural Networks (DNNs) are increasingly deployed in many real-world applications e.g., cloud prediction APIs. Recent advances in model functionality stealing attacks via black-box access (i.e., inputs in, predictions…

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 malicious applications of deep forgery, represented by face swapping, have introduced security threats such as misinformation dissemination and identity fraud. While some research has proposed the use of robust watermarking methods to…

Deep learning (DL) offers potential improvements throughout the CAD tool-flow, one promising application being lithographic hotspot detection. However, DL techniques have been shown to be especially vulnerable to inference and training time…

The use of machine learning (ML) has become increasingly prevalent in various domains, highlighting the importance of understanding and ensuring its safety. One pressing concern is the vulnerability of ML applications to model stealing…

Ensuring the legal usage of deep models is crucial to promoting trustable, accountable, and responsible artificial intelligence innovation. Current passport-based methods that obfuscate model functionality for license-to-use and ownership…

To avoid detection, adversaries often use command-line obfuscation. There are numerous techniques of the command-line obfuscation, all designed to alter the command-line syntax without affecting its original functionality. This variability…

A novel framework of optical image hiding based on deep learning (DL) is proposed in this paper, and hidden information can be reconstructed from an interferogram by using an end to end network with high-quality. By using the prior data…

Deep Learning (DL) is rapidly maturing to the point that it can be used in safety- and security-crucial applications. However, adversarial samples, which are undetectable to the human eye, pose a serious threat that can cause the model to…