Research Assistant Professor @USC-ISI
๐ค I investigate malicious activity on social media networks ๐ต๐ผ
We introduce a new framework for detecting coordination in video-first platforms, uncovering influence campaigns using synthetic voices, split-screen tactics, and cross-account duplication.
๐https://arxiv.org/abs/2505.10867
@emilioferrara.bsky.social
๐ Paper: arxiv.org/pdf/2510.25003
๐ Interactive Dashboard: llmxio-dashboard.vercel.app
๐งญ Curious how this plays out? An interactive dashboard lets you inspect agent behaviors, network evolution, and coordination dynamics directly.
- Malign agents' networks become denser & more clustered;
- Interactions grow more reciprocal & increasingly positive;
- Narratives converge toward greater semantic homogeneity;
- Amplification becomes synchronized.
Give AI agents just a bit of awareness of their โteammates,โ and they begin to self-organize. No scripts. No central command. Justย networked AI learning how to act together.
Reposted by Fabio Giglietto, Timothy Graham
Can AI agents coordinate influence campaigns without human guidance? And how does coordination arise among AI agents? In our latest research, we simulate LLM-powered AI agents acting like users on an online platform, some benign, some running an influence operation
Reposted by Luca Luceri
Building on discourse networks work with @hanshanley.bsky.social @luceriluc.bsky.social @emilioferrara.bsky.socialโthis lets us visualize the online landscape as a unified system, rather than isolating each platform.
Synthetic Politics: Prevalence, Spreaders, and Emotional Reception of AI-Generated Political Images on X | Proceedings of the 36th ACM Conference on Hypertext and Social Media
dl.acm.org/doi/10.1145/...
Reposted by Luca Luceri
Online โlikesโ for toxic social media posts prompt more โ and more hateful โ messages
https://theconversation.com/online-likes-for-toxic-social-media-posts-prompt-more-and-more-hateful-messages-218220
Reposted by Luca Luceri
Reposted by Luca Luceri
w/ @luceriluc.bsky.social , Julie Jiang, @emilioferrara.bsky.social
Explore our findings: arxiv.org/abs/2406.11553
Reposted by Luca Luceri
This is the result of an incredible collaboration with @luceriluc.bsky.social @frafabbri.bsky.social and @emilioferrara.bsky.social
Read the entire thread for a summary and the link to the preprint.
Reposted by Luca Luceri
Reposted by Luca Luceri
https://www.ft.com/content/743c1dec-0c5c-4c39-a940-830ce156c235
Reposted by Luca Luceri
"The Susceptibility Paradox in Online Social Influenceโ by @luceriluc.bsky.social, @jinyiye.bsky.social, Julie Jiang & @emilioferrara.bsky.social was named a Top 5 Paper & won Best Paper Honorable Mention!
๐ Congrats to all!
Reposted by Luca Luceri
Don't miss our work with @frapierri.bsky.social, Stefano Cresci, @luceriluc.bsky.social, @pettertornberg.com and @silviagiordano.bsky.social here: ojs.aaai.org/index.php/IC...
Reposted by Luca Luceri
Researchers made 120 sock puppet accounts to see whose content is getting pushed on users. #FAccT2025
@jinyiye.bsky.social @luceriluc.bsky.social @emilioferrara.bsky.social
doi.org/10.1145/3715...