Paper deep dive
Exploring Privacy and Security Risks in LLMs: Data Leakage, Prompt Injection, and Membership Inference
Giancarlo Sperlì
Intelligence
Status: succeeded | Model: google/gemini-3.1-flash-lite-preview | Prompt: intel-v1 | Confidence: 93%
Last extracted: 3/11/2026, 12:46:00 AM
Summary
This paper analyzes the dual role of Large Language Models (LLMs) in multimedia security, evaluating their potential to enhance defensive cybersecurity frameworks while simultaneously introducing vulnerabilities such as data leakage, prompt injection, and membership inference attacks.
Entities (5)
Relation Signals (4)
Large Language Models → exhibitsvulnerability → Data Leakage
confidence 90% · their susceptibility to attacks such as data leakage
Large Language Models → exhibitsvulnerability → Prompt Injection
confidence 90% · their susceptibility to attacks such as prompt injection
Large Language Models → exhibitsvulnerability → Membership Inference
confidence 90% · We focus our analysis on privacy-oriented threats, including... membership inference
Large Language Models → usedin → Cyber Kill Chain
confidence 85% · we explore the constructive application of LLMs within cybersecurity frameworks, such as the Cyber Kill Chain
Cypher Suggestions (0)
No Cypher suggestions yet.
Abstract
In this paper, we present an analysis of the dual role of Large Language Models (LLMs) in the context of multimedia security, examining how these models can both strengthen defensive capabilities and introduce new vulnerabilities within modern content ecosystems. As LLMs increasingly interface with multimedia workflows-ranging from text-image generation pipelines to cross-modal retrieval and content moderation-their susceptibility to attacks such as data leakage, prompt injection, and jailbreaks raises critical concerns for the integrity and trustworthiness of multimedia platforms. We focus our analysis on privacy-oriented threats, including model inversion and membership inference, and discuss their implications for systems that process or generate multimedia content. Building on this risk landscape, we outline principles for improving the robustness and resilience of LLM-driven multimedia applications, highlighting strategies suited to in-the-wild threat scenarios. Indeed, we explore the constructive application of LLMs within cybersecurity frameworks, such as the Cyber Kill Chain, demonstrating how these models can be leveraged for threat detection, risk assessment, and automated defensive operations.
Tags
Links
Full Text
851 characters extracted from source content.
Expand or collapse full text
Exploring Privacy and Security Risks in LLMs: Data Leakage, Prompt Injection, and Membership Inference | IEEE Conference Publication | IEEE Xplore IEEE Account Change Username/Password Update Address Purchase Details Payment Options Order History View Purchased Documents Profile Information Communications Preferences Profession and Education Technical Interests Need Help? US & Canada: +1 800 678 4333 Worldwide: +1 732 981 0060 Contact & Support About IEEE Xplore Contact Us Help Accessibility Terms of Use Nondiscrimination Policy Sitemap Privacy & Opting Out of Cookies A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.© Copyright 2026 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.