Related papers: PATCH: Mitigating PII Leakage in Language Models w…

The leakage of data might have been an extreme effect on the personal level if it contains sensitive information. Common prevention methods like encryption-decryption, endpoint protection, intrusion detection system are prone to leakage.…

Large multimodal language models have proven transformative in numerous applications. However, these models have been shown to memorize and leak pre-training data, raising serious user privacy and information security concerns. While data…

Are Large Pre-Trained Language Models Leaking Your Personal Information? In this paper, we analyze whether Pre-Trained Language Models (PLMs) are prone to leaking personal information. Specifically, we query PLMs for email addresses with…

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…

Removing personally identifiable information (PII) from texts is necessary to comply with various data protection regulations and to enable data sharing without compromising privacy. However, recent works show that documents sanitized by…

Pre-trained language models (PLMs) have demonstrated significant proficiency in solving a wide range of general natural language processing (NLP) tasks. Researchers have observed a direct correlation between the performance of these models…

Neural networks trained on real-world data often exhibit biases while simultaneously being vulnerable to privacy attacks aimed at extracting sensitive information. Despite extensive research on each problem individually, their intersection…

System prompts are widely used to guide the outputs of large language models (LLMs). These prompts often contain business logic and sensitive information, making their protection essential. However, adversarial and even regular user queries…

Recently, self-supervised learning (SSL) was shown to be vulnerable to patch-based data poisoning backdoor attacks. It was shown that an adversary can poison a small part of the unlabeled data so that when a victim trains an SSL model on…

We consider the privacy-preserving machine learning (ML) setting where the trained model must satisfy differential privacy (DP) with respect to the labels of the training examples. We propose two novel approaches based on, respectively, the…

Phishing sites continue to grow in volume and sophistication. Recent work leverages large language models (LLMs) to analyze URLs, HTML, and rendered content to decide whether a website is a phishing site. While these approaches are…

Although language models (LMs) demonstrate exceptional capabilities on various tasks, they are potentially vulnerable to extraction attacks, which represent a significant privacy risk. To mitigate the privacy concerns of LMs, machine…

When users submit queries to Large Language Models (LLMs), their prompts can often contain sensitive data, forcing a difficult choice: Send the query to a powerful proprietary LLM providers to achieving state-of-the-art performance and risk…

Information leakage to a guessing adversary in index coding is studied, where some messages in the system are sensitive and others are not. The non-sensitive messages can be used by the server like secret keys to mitigate leakage of the…

The privacy concerns associated with the use of Large Language Models (LLMs) have grown recently with the development of LLMs such as ChatGPT. Differential Privacy (DP) techniques are explored in existing work to mitigate their privacy…

Vision Language Models (VLMs) are increasingly integrated into privacy-critical domains, yet existing evaluations of personally identifiable information (PII) leakage largely treat privacy as a static extraction task and ignore how a…

Large language models (LLMs) have become the backbone of modern natural language processing but pose privacy concerns about leaking sensitive training data. Membership inference attacks (MIAs), which aim to infer whether a sample is…

Differential privacy (DP) offers a theoretical upper bound on the potential privacy leakage of analgorithm, while empirical auditing establishes a practical lower bound. Auditing techniques exist forDP training algorithms. However machine…

Local differential privacy (LDP) has emerged as a promising paradigm for privacy-preserving data collection in distributed systems, where users contribute multi-dimensional records with potentially correlated attributes. Recent work has…

Security concerns in large-scale networked environments are becoming increasingly critical. To further improve the algorithm security from the design perspective of decentralized optimization algorithms, we introduce a new measure: Privacy…