Related papers: SELF: A Robust Singular Value and Eigenvalue Appro…

The connectivity and resource-constrained nature of single-board devices open the door to cybersecurity concerns affecting Internet of Things (IoT) scenarios. One of the most important issues is the presence of unauthorized IoT devices that…

The behavior of LLMs does not depend solely on the model itself. Components of the inference system, such as the inference engine, attention backend, and hardware platform, subtly influence how inputs are processed. These components differ…

Protecting the intellectual property of Large Language Models (LLMs) has become increasingly critical due to the high cost of training. Model merging, which integrates multiple expert models into a single multi-task model, introduces a…

The pervasive integration of Indoor Positioning Systems (IPS) arises from the limitations of Global Navigation Satellite Systems (GNSS) in indoor environments, leading to the widespread adoption of Location-Based Services (LBS) in places…

This paper introduces a novel self-consciousness defense mechanism for Large Language Models (LLMs) to combat prompt injection attacks. Unlike traditional approaches that rely on external classifiers, our method leverages the LLM's inherent…

Large language models(LLMs) are currently at the forefront of the machine learning field, which show a broad application prospect but at the same time expose some risks of privacy leakage. We combined Fully Homomorphic Encryption(FHE) and…

The evolution of Large Language Models (LLMs) into agentic systems that perform autonomous reasoning and tool use has created significant intellectual property (IP) value. We demonstrate that these systems are highly vulnerable to imitation…

With the growing applications of Deep Learning (DL), especially recent spectacular achievements of Large Language Models (LLMs) such as ChatGPT and LLaMA, the commercial significance of these remarkable models has soared. However, acquiring…

Model fingerprint detection has shown promise to trace the provenance of AI-generated images in forensic applications. However, despite the inherent adversarial nature of these applications, existing evaluations rarely consider adversarial…

Releasing open-source large language models (LLMs) presents a dual-use risk since bad actors can easily fine-tune these models for harmful purposes. Even without the open release of weights, weight stealing and fine-tuning APIs make closed…

We introduce LLMmap, a first-generation fingerprinting technique targeted at LLM-integrated applications. LLMmap employs an active fingerprinting approach, sending carefully crafted queries to the application and analyzing the responses to…

Directly releasing those data raises privacy and liability (e.g., due to unauthorized distribution of such datasets) concerns since location data contain users' sensitive information, e.g., regular moving patterns and favorite spots. To…

The jailbreak attack can bypass the safety measures of a Large Language Model (LLM), generating harmful content. This misuse of LLM has led to negative societal consequences. Currently, there are two main approaches to address jailbreak…

The rise of reinforcement learning (RL) in critical real-world applications demands a fundamental rethinking of privacy in AI systems. Traditional privacy frameworks, designed to protect isolated data points, fall short for sequential…

The rapid growth of large language models raises pressing concerns about intellectual property protection under black-box deployment. Existing backdoor-based fingerprints either rely on rare tokens -- leading to high-perplexity inputs…

The proliferation of large language models (LLMs) has intensified concerns over model theft and license violations, necessitating robust and stealthy ownership verification. Existing fingerprinting methods either require impractical…

Currently, deep learning models are easily exposed to data leakage risks. As a distributed model, Split Learning thus emerged as a solution to address this issue. The model is splitted to avoid data uploading to the server and reduce…

The increasing use of Artificial Intelligence (AI) technologies, such as Large Language Models (LLMs) has led to nontrivial improvements in various tasks, including accurate authorship identification of documents. However, while LLMs…

A "wireless fingerprint" which exploits hardware imperfections unique to each device is a potentially powerful tool for wireless security. Such a fingerprint should be able to distinguish between devices sending the same message, and should…

Recent advances in large language models (LLMs) have yielded impressive performance on various tasks, yet they often depend on high-quality feedback that can be costly. Self-refinement methods attempt to leverage LLMs' internal evaluation…