Related papers: Practical Attacks Against Privacy and Availability…
Large language models (LLMs) demonstrate powerful information handling capabilities and are widely integrated into chatbot applications. OpenAI provides a platform for developers to construct custom GPTs, extending ChatGPT's functions and…
Computers and computer networks have become integral to virtually every aspect of modern life, with the Internet playing an indispensable role. Organizations, businesses, and individuals now store vast amounts of proprietary, confidential,…
Device-to-Device (D2D) communication is mainly launched by the transmission requirements between devices for specific applications such as Proximity Services in Long-Term Evolution Advanced (LTE-A) networks, and each application will form a…
The fourth generation of cell phones, marketed as 4G/LTE (Long-Term Evolution) is being quickly adopted worldwide. Given the mobile and wireless nature of the involved communications, security is crucial. This paper includes both a…
Machine-to-Machine (M2M) communications are one of the major drivers of the cellular network evolution towards 5G systems. One of the key challenges is on how to provide reliability guarantees to each accessing device in a situation in…
Internet of Things (IoT) devices are becoming ubiquitous in our lives, with applications spanning from the consumer domain to commercial and industrial systems. The steep growth and vast adoption of IoT devices reinforce the importance of…
The widespread deployment of LLM-based agents is likely to introduce a critical privacy threat: malicious agents that proactively engage others in multi-turn interactions to extract sensitive information. However, the evolving nature of…
Commercial cellular telecommunications networks are routinely used as key means of voice and data transport by both businesses and the Public. Despite advances in encryption and other security measures, these commercial cellular networks…
Pre-trained language models (PTLMs) have achieved great success and remarkable performance over a wide range of natural language processing (NLP) tasks. However, there are also growing concerns regarding the potential security issues in the…
The success and wide adoption of generative AI (GenAI), particularly large language models (LLMs), has attracted the attention of cybercriminals seeking to abuse models, steal sensitive data, or disrupt services. Moreover, providing…
Lateral movement is a crucial component of advanced persistent threat (APT) attacks in networks. Attackers exploit security vulnerabilities in internal networks or IoT devices, expanding their control after initial infiltration to steal…
Federated learning (FL) is an emerging distributed machine learning paradigm proposed for privacy preservation. Unlike traditional centralized learning approaches, FL enables multiple users to collaboratively train a shared global model…
Massive Machine-Type Communications (MTC) over cellular networks is expected to be an integral part of wireless "Smart City" applications. The Long Term Evolution (LTE)/LTE-Advanced (LTE-A) technology is a major candidate for provisioning…
We introduce LTrack, a new tracking attack on LTE that allows an attacker to stealthily extract user devices' locations and permanent identifiers (IMSI). To remain stealthy, the localization of devices in LTrack is fully passive, relying on…
While open Large Language Models (LLMs) have made significant progress, they still fall short of matching the performance of their closed, proprietary counterparts, making the latter attractive even for the use on highly private data.…
Local differential privacy is a widely studied restriction on distributed algorithms that collect aggregates about sensitive user data, and is now deployed in several large systems. We initiate a systematic study of a fundamental limitation…
Recent Searchable Symmetric Encryption (SSE) schemes enable secure searching over an encrypted database stored in a server while limiting the information leaked to the server. These schemes focus on hiding the access pattern, which refers…
Large Language Models (LLMs) have transformed software development, enabling AI-powered applications known as LLM-based agents that promise to automate tasks across diverse apps and workflows. Yet, the security implications of deploying…
Adversarial attacks by malicious users that threaten the safety of large language models (LLMs) can be viewed as attempts to infer a target property $T$ that is unknown when an instruction is issued, and becomes knowable only after the…
Fine-tuning has emerged as a critical process in leveraging Large Language Models (LLMs) for specific downstream tasks, enabling these models to achieve state-of-the-art performance across various domains. However, the fine-tuning process…