相关论文: Zero-Trust Artificial Intelligence Model Security …

In recent years, large language models (LLMs) have demonstrated notable success across various tasks, but the trustworthiness of LLMs is still an open problem. One specific threat is the potential to generate toxic or harmful responses.…

By exploiting the increasing surface attack of systems, cyber-attacks can cause catastrophic events, such as, remotely disable safety mechanisms. This means that in order to avoid hazards, safety and security need to be integrated,…

The growing complexity of cyber attacks has necessitated the evolution of firewall technologies from static models to adaptive, machine learning-driven systems. This research introduces "Dynamically Retrainable Firewalls", which respond to…

The size of deep learning models in artificial intelligence (AI) software is increasing rapidly, which hinders the large-scale deployment on resource-restricted devices (e.g., smartphones). To mitigate this issue, AI software compression…

The widespread adoption of Large Language Models (LLMs) has revolutionized AI deployment, enabling autonomous and semi-autonomous applications across industries through intuitive language interfaces and continuous improvements in model…

When training a machine learning model, it is standard procedure for the researcher to have full knowledge of both the data and model. However, this engenders a lack of trust between data owners and data scientists. Data owners are…

Backdoor attacks present a serious security threat to deep neuron networks (DNNs). Although numerous effective defense techniques have been proposed in recent years, they inevitably rely on the availability of either clean or poisoned data.…

Model stealing attacks present a dilemma for public machine learning APIs. To protect financial investments, companies may be forced to withhold important information about their models that could facilitate theft, including uncertainty…

In this paper, we propose a model protection method by using block-wise pixel shuffling with a secret key as a preprocessing technique to input images for the first time. The protected model is built by training with such preprocessed…

This article considers the design and analysis of multiple moving target defenses for recognizing and isolating attacks on cyber-physical systems. We consider attackers who perform integrity attacks on a set of sensors and actuators in a…

Context:With the advancement of artificial intelligence (AI) technology and applications, numerous AI models have been developed, leading to the emergence of open-source model hosting platforms like Hugging Face (HF). Thanks to these…

The proliferation of retrieval-augmented generation (RAG) has established vector databases as critical infrastructure, yet they introduce severe privacy risks via embedding inversion attacks. Existing paradigms face a fundamental trade-off:…

This paper presents a novel reconstruction method that leverages Diffusion Models to protect machine learning classifiers against adversarial attacks, all without requiring any modifications to the classifiers themselves. The susceptibility…

Machine learning model repositories such as the Hugging Face Model Hub facilitate model exchanges. However, bad actors can deliver malware through compromised models. Existing defenses such as safer model formats, restrictive (but…

Traditional cybersecurity methodologies target deterministic systems and fail to address the probabilistic nature of AI, leaving systems vulnerable to attack vectors such as model inversion, data poisoning, and prompt injection. Recent…

Machine learning (ML) models serve as powerful tools for threat detection and mitigation; however, they also introduce potential new risks. Adversarial input can exploit these models through standard interfaces, thus creating new attack…

Traditional security architectures are becoming more vulnerable to distributed attacks due to significant dependence on trust. This will further escalate when implementing agentic AI within the systems, as more components must be secured…

The challenge of WAD (web attack detection) is growing as hackers continuously refine their methods to evade traditional detection. Deep learning models excel in handling complex unknown attacks due to their strong generalization and…

Neural networks are widely known to be vulnerable to backdoor attacks, a method that poisons a portion of the training data to make the target model perform well on normal data sets, while outputting attacker-specified or random categories…

In the rapidly evolving field of artificial intelligence, machine learning emerges as a key technology characterized by its vast potential and inherent risks. The stability and reliability of these models are important, as they are frequent…