Related papers: PILLAR: an AI-Powered Privacy Threat Modeling Tool

Large language models (LLMs) are increasingly deployed in interactive and retrieval-augmented settings, raising significant privacy concerns. While attacks such as Membership Inference (MIA), Attribute Inference (AIA), Data Extraction…

Threat modeling is a crucial component of cybersecurity, particularly for industries such as banking, where the security of financial data is paramount. Traditional threat modeling approaches require expert intervention and manual effort,…

Safety backdoor attacks in large language models (LLMs) enable the stealthy triggering of unsafe behaviors while evading detection during normal interactions. The high dimensionality of potential triggers in the token space and the diverse…

The exponential growth of cyber threat knowledge, exemplified by the expansion of databases such as MITRE-CVE and NVD, poses significant challenges for cyber threat analysis. Security professionals are increasingly burdened by the sheer…

Recent advances in multi-modal Large Language Models (M-LLMs) have demonstrated a powerful ability to synthesize implicit information from disparate sources, including images and text. These resourceful data from social media also introduce…

For systems whose states implicate sensitive information, their privacy is of great concern. While notions like differential privacy have been successfully introduced to dynamical systems, it is still unclear how a system's privacy can be…

Fine-tuning large language models (LLMs) has become an essential strategy for adapting them to specialized tasks; however, this process introduces significant privacy challenges, as sensitive training data may be inadvertently memorized and…

While robots have previously utilized rule-based systems or probabilistic models for user interaction, the rapid evolution of large language models (LLMs) presents new opportunities to develop LLM-powered robots for enhanced human-robot…

The performance of modern machine learning systems depends on access to large, high-quality datasets, often sourced from user-generated content or proprietary, domain-specific corpora. However, these rich datasets inherently contain…

As language models (LMs) are widely utilized in personalized communication scenarios (e.g., sending emails, writing social media posts) and endowed with a certain level of agency, ensuring they act in accordance with the contextual privacy…

Large Language Model (LLM) agents have achieved rapid adoption and demonstrated remarkable capabilities across a wide range of applications. To improve reasoning and task execution, modern LLM agents would incorporate memory modules or…

Large Language Models (LLMs) have transformed artificial intelligence by advancing natural language understanding and generation, enabling applications across fields beyond healthcare, software engineering, and conversational systems.…

Machine learning (ML) models frequently rely on training data that may include sensitive or personal information, raising substantial privacy concerns. Legislative frameworks such as the General Data Protection Regulation (GDPR) and the…

In-context learning (ICL) in Large Language Models (LLMs) has shown remarkable performance across various tasks without requiring fine-tuning. However, recent studies have highlighted the risk of private data leakage through the prompt in…

Large language models (LLMs) are increasingly used to assist developers with code, yet their implementations of cryptographic functionality often contain exploitable flaws. Minor design choices (e.g., static initialization vectors or…

Retrieval-augmented generation (RAG) is a powerful technique to facilitate language model with proprietary and private data, where data privacy is a pivotal concern. Whereas extensive research has demonstrated the privacy risks of large…

Recently, powerful Large Language Models (LLMs) have become easily accessible to hundreds of millions of users world-wide. However, their strong capabilities and vast world knowledge do not come without associated privacy risks. In this…

Current techniques for privacy auditing of large language models (LLMs) have limited efficacy -- they rely on basic approaches to generate canaries which leads to weak membership inference attacks that in turn give loose lower bounds on the…

As Large Language Models (LLMs) increasingly become key components in various AI applications, understanding their security vulnerabilities and the effectiveness of defense mechanisms is crucial. This survey examines the security challenges…

Despite being empowered with alignment mechanisms, large language models (LLMs) are increasingly vulnerable to emerging jailbreak attacks that can compromise their alignment mechanisms. This vulnerability poses significant risks to…