5 citations · 5 across the 4 of their papers we have counts for
6 papers
Omniscience for the Masses: New Threats in the Metaverse's Democratized World Creation
Andrea Mengascini, Ryan Aurelio, Jason Polakis +1
Metaverse platforms increasingly derive their success from user-generated virtual worlds: self-contained social and interactive environments, which can be created by any ordinary u…
Indirect Prompt Injection in the Wild: An Empirical Study of Prevalence, Techniques, and Objectives
Soheil Khodayari, Xuenan Zhang, Bhupendra Acharya +1
As LLMs are increasingly integrated into systems that browse, retrieve, summarize, and act on web content, webpages have become an untrusted input vector for downstream model behav…
Behind the Curtain: How Shared Hosting Providers Respond to Vulnerability Notifications
Giada Stivala, Rafael Mrowczynski, Maria Hellenthal +1
Large-scale vulnerability notifications (VNs) can help hosting provider organizations (HPOs) identify and remediate security vulnerabilities that attackers can exploit in data brea…
Exploration of the Dynamics of Buy and Sale of Social Media Accounts
Mario Beluri, Bhupendra Acharya, Soheil Khodayari +3
There has been a rise in online platforms facilitating the buying and selling of social media accounts. While the trade of social media profiles is not inherently illegal, social m…
Uncovering the Role of Support Infrastructure in Clickbait PDF Campaigns
Giada Stivala, Gianluca De Stefano, Andrea Mengascini +2
Clickbait PDFs, an entry point for multiple Web attacks, are distributed via SEO poisoning and rank high in search results due to being massively uploaded on abused or compromised…
Rag and Roll: An End-to-End Evaluation of Indirect Prompt Manipulations in LLM-based Application Frameworks
Gianluca De Stefano, Lea Schönherr, Giancarlo Pellegrino
Retrieval Augmented Generation (RAG) is a technique commonly used to equip models with out of distribution knowledge. This process involves collecting, indexing, retrieving, and pr…