Related papers: PIIGuard: Mitigating PII Harvesting under Adversar…
When large language models are trained on private data, it can be a significant privacy risk for them to memorize and regurgitate sensitive information. In this work, we propose a new practical data extraction attack that we call "neural…
The need for secure and private Artificial Intelligence (AI) and Machine Learning (ML) on edge and mobile devices has increased the necessity of protecting the architecture of these systems from threats to both security and privacy. With an…
Users increasingly rely on large language models (LLMs) for personal, emotionally charged, and socially sensitive conversations. However, prompts sent to cloud-hosted models can contain personally identifiable information (PII) that users…
The recent growth in the use of Large Language Models has made them vulnerable to sophisticated adversarial assaults, manipulative prompts, and encoded malicious inputs. Existing countermeasures frequently necessitate retraining models,…
The rapid development of large language models (LLMs) has yielded impressive success in various downstream tasks. However, the vast potential and remarkable capabilities of LLMs also raise new security and privacy concerns if they are…
In membership inference attacks (MIAs), an adversary observes the predictions of a model to determine whether a sample is part of the model's training data. Existing MIA defenses conceal the presence of a target sample through strong…
Federated Learning (FL) enables clients to collaboratively train a global model using their local datasets while reinforcing data privacy, but it is prone to poisoning attacks. Existing defense mechanisms assume that clients' data are…
Iterative jailbreak methods that repeatedly rewrite and input prompts into large language models (LLMs) to induce harmful outputs -- using the model's previous responses to guide each new iteration -- have been found to be a highly…
Large language models (LLMs) have emerged as a promising phishing detection mechanism, addressing the limitations of traditional deep learning-based detectors, including poor generalization to previously unseen websites and a lack of…
The rapid advancement and widespread use of large language models (LLMs) have raised significant concerns regarding the potential leakage of personally identifiable information (PII). These models are often trained on vast quantities of…
With the increasing use of conversational AI systems, there is growing concern over privacy leaks, especially when users share sensitive personal data in interactions with Large Language Models (LLMs). Conversations shared with these models…
Each month, more attacks are launched with the aim of making web users believe that they are communicating with a trusted entity which compels them to share their personal, financial information. Phishing costs Internet users billions of…
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…
LLM-powered chatbots are becoming widely adopted in applications such as healthcare, personal assistants, industry hiring decisions, etc. In many of these cases, chatbots are fed sensitive, personal information in their prompts, as samples…
Large Language Models (LLMs) are increasingly being integrated into various applications. The functionalities of recent LLMs can be flexibly modulated via natural language prompts. This renders them susceptible to targeted adversarial…
Device logs are essential for forensic investigations, enterprise monitoring, and fraud detection; however, they often leak personally identifiable information (PII) when exported for third-party analysis. Existing approaches either fail to…
Website fingerprinting (WF) is a well-know threat to users' web privacy. New internet standards, such as QUIC, include padding to support defenses against WF. Previous work only analyzes the effectiveness of defenses when users are behind a…
The emergence of Large Language Models (LLMs), including ChatGPT, is having a significant impact on a wide range of fields. While LLMs have been extensively researched for tasks such as code generation and text synthesis, their application…
Model Inversion Attacks (MIAs) pose a significant threat to data privacy by reconstructing sensitive training samples from the knowledge embedded in trained machine learning models. Despite recent progress in enhancing the effectiveness of…
Concerns regarding Large Language Models (LLMs) to memorize and disclose private information, particularly Personally Identifiable Information (PII), become prominent within the community. Many efforts have been made to mitigate the privacy…