相关论文: Disarming Steganography Attacks Inside Neural Netw…

In deployment and application, large language models (LLMs) typically undergo safety alignment to prevent illegal and unethical outputs. However, the continuous advancement of jailbreak attack techniques, designed to bypass safety…

Deep Neural Networks exhibit inherent vulnerabilities to adversarial attacks, which can significantly compromise their outputs and reliability. While existing research primarily focuses on attacking single-task scenarios or indiscriminately…

The field of steganography has long been focused on developing methods to securely embed information within various digital media while ensuring imperceptibility and robustness. However, the growing sophistication of detection tools and the…

In the rapidly evolving landscape of communication and network security, the increasing reliance on deep neural networks (DNNs) and cloud services for data processing presents a significant vulnerability: the potential for backdoors that…

Deep learning models are vulnerable to adversarial examples which are input samples modified in order to maximize the error on the system. We introduce Spartan Networks, resistant deep neural networks that do not require input preprocessing…

Securing neural networks (NNs) against model extraction and parameter exfiltration attacks is an important problem primarily because modern NNs take a lot of time and resources to build and train. We observe that there are no…

Deep neural networks have proven to be quite effective in a wide variety of machine learning tasks, ranging from improved speech recognition systems to advancing the development of autonomous vehicles. However, despite their superior…

Deep neural networks (DNNs) have proven to be quite effective in a vast array of machine learning tasks, with recent examples in cyber security and autonomous vehicles. Despite the superior performance of DNNs in these applications, it has…

While advanced machine learning (ML) models are deployed in numerous real-world applications, previous works demonstrate these models have security and privacy vulnerabilities. Various empirical research has been done in this field.…

Resistive Random Access Memory (ReRAM) has emerged as a promising platform for deep neural networks (DNNs) due to its support for parallel in-situ matrix-vector multiplication. However, hardware failures, such as stuck-at-fault defects, can…

With the growth of model sizes and the scale of their deployment, their sheer size burdens the infrastructure requiring more network and more storage to accommodate these. While there is a vast model compression literature deleting parts of…

Outsourced deep neural networks have been demonstrated to suffer from patch-based trojan attacks, in which an adversary poisons the training sets to inject a backdoor in the obtained model so that regular inputs can be still labeled…

Deep learning has shown great promise in the domain of medical image analysis. Medical professionals and healthcare providers have been adopting the technology to speed up and enhance their work. These systems use deep neural networks (DNN)…

With the advance in malware technology, attackers create new ways to hide their malicious code from antivirus services. One way to obfuscate an attack is to use common files as cover to hide the malicious scripts, so the malware will look…

This paper investigates the critical issue of data poisoning attacks on AI models, a growing concern in the ever-evolving landscape of artificial intelligence and cybersecurity. As advanced technology systems become increasingly prevalent…

Backdoor attacks compromise the integrity and reliability of machine learning models by embedding a hidden trigger during the training process, which can later be activated to cause unintended misbehavior. We propose a novel backdoor…

In the rapid advancement of artificial intelligence, privacy protection has become crucial, giving rise to machine unlearning. Machine unlearning is a technique that removes specific data influences from trained models without the need for…

Research into AI alignment has grown considerably since the recent introduction of increasingly capable Large Language Models (LLMs). Unfortunately, modern methods of alignment still fail to fully prevent harmful responses when models are…

We propose a novel method for protecting trained models with a secret key so that unauthorized users without the correct key cannot get the correct inference. By taking advantage of transfer learning, the proposed method enables us to train…

Model stealing, i.e., unauthorized access and exfiltration of deep learning models, has become one of the major threats. Proprietary models may be protected by access controls and encryption. However, in reality, these measures can be…