🔥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

👥 Frustrated by chatbots remembering what you said, but never use the memory correctly? We evaluated 15 SoTA LLM chatbots' ability to apply the memory about a user in downstream tasks. Introducing: 𝑷𝒆𝒓𝒔𝒐𝒏𝒂𝑴𝒆𝒎 Benchmark 🥇Gemini 1.5, GPT4.5, GPT4.1 are in the lead ⬇️

Come chat with us tomorrow on coding!

Check out the great recent PhD grad and uber HCI hacker ⁦Jackie Yang⁩ on the last cool piece of his LLM-powered multimodal dev tool! See at #chi2025 at 4:20 in G304! dl.acm.org/doi/10.1145/37… programs.sigchi.org/chi/2025/progr…

1/ 🧵 How does #DifferentialPrivacy affect #hallucinations in LLMs? We find that while DP-SGD *reduces* some hallucinations, it introduces new types of linguistic errors. Join Ivoline Ngong’s oral 2 PM Ballroom B TODAY @NAACL to learn how our method, DPRefine, addresses these

Super excited to participate in OpenAI Security Research Conference to talk about our PrivacyLens project and some recent exploration. I will be around from 5/1 to 5/2. DMs are open if you want to chat about agents/human-in-the-loop/sandboxing! events.openai.com/oaisecurity

Great job, Anna and Eric! Anna presented our work demonstrating the inconsistency of LLM responses and how attackers might take advantage (doi.org/10.1145/370659…); and Eric investigating health-related tracking and deceptive ads (doi.org/10.1145/370659…) Matthew McCoy

📢 Hey folks, are you interested in Humans + AI privacy & security? Let’s talk! Join us for the HAIPS workshop (haips.com) at ACM CCS 2024 #CCS2025 .

Come see what the hype is about at the nexus of #Security and #privacy, #HCI, and #AI at the #HAIPS2025 workshop at #CCS2025 Send us your tired, your poor, Your huddled masses yearning to breathe free, and papers you just had rejected from #usesec25 or #ICML2025

📣Thrilled to announce I’ll join Carnegie Mellon University (CMU Engineering & Public Policy & Language Technologies Institute | @CarnegieMellon) as an Assistant Professor starting Fall 2026! Until then, I’ll be a Research Scientist at AI at Meta FAIR in SF, working with Kamalika Chaudhuri’s amazing team on privacy, security, and reasoning in LLMs!

Will AI agents be controlled by big tech companies? Or could they be controlled by users, safeguarding user autonomy and privacy? In a new position paper (accepted to ICML 2025), we outline the steps we need to take now to enable user-centric agents (w/Seth Lazar, Noam Kolt)🧶

📢 We now have two amazing keynote speakers lined up for #HAIPS2025 (the 1st Workshop on Human-Centered AI, Privacy, and Security)! Jason Hong and Patrick Gage Kelley Submit your: - Original papers - Encore papers - SoK papers - Vision papers by June 20th! 💻haips.com

🤩🤩

We finally answer “do real membership inference attacks really work on lllms?” Super fun collaboration that started out as a conversation in Neurips!

I think the pressing question is: is our peer review system ready to handle a potential wave of agent-generated papers? right now I don’t think it is (yet)

Really interesting work on what kinds of automation workers truly desire. Congratulations!

Still one week left before the workshop deadline!