🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Day 4 of #CHI2023 Have been enjoying paper sessions and being an SV! (worked as floor monitor this morning 😆) #reCHInnecting

😆

tranquility after raining days the summer is gone 🍃

Made my office hour ‘debut’ as a TA last Friday but no one came to the session throughout the two hours 🥹

For any CS PhD applicants this year: 'Grad app support programs' give informal feedback (on statements, etc) from current PhD students before formally applying. Valuable stuff. Made a 2024 tracker. Feel free to share! +Reach out if one's missing. 👇 andrewkuz.net/public/dashboa…

some good news in the busy application season #CHI2024 See you in Hawaii!! ☺️

done with the last assignment of my undergrad. getting ready for leaving Hong Kong the past few years feel like a long long dream separation anxiety at its peak 🥲

SFL Social Futures Lab current members and alumni at #chi2024! We’ve got Tony Li, Kevin Feng @ CHI, Shagun Jhaver, Lawrence Tan, Nick Vincent, Gloria Bingcan Guo @CHI2025, Leijie Wang, Emelia ✨ @CSCW2024, and Alicia Guo!!!

Mitigating racial bias from LLMs is a lot easier than removing it from humans! Can’t believe this happened at the best AI conference NeurIPS Conference We have ethical reviews for authors, but missed it for invited speakers? 😡

7/🧵The Obvious Invisible Threat: LLM-Powered GUI Agents’ Vulnerability to Fine-Print Injections This paper reveals that LLM-powered GUI agents are highly vulnerable to adversarial attacks, particularly through Fine-Print Injection, highlighting significant privacy and security

We studied how GUI agents like OpenAI Operator and Claude behave under privacy & security threats. We find: ❌ Fine-Print Injection worked up to 74% of the time. ❌ Humans performed even worse than the agents. Here’s a 30-second flash video of what we found 👇 #LLM #privacy #AI

🫶

🚨New workshop at ACM CCS 2024 #CCS2025! Glad to announce the 1st workshop on Human-Centered AI Privacy and Security (#HAIPS2025, pronounced “hypes” 😎) AI is reshaping lives and S&P research—let’s bring people back to the center. 📢 CFP is out! 🌊 haips.com