Pinned Tweet
Our Team Hoosiers won the🥇place in the AI Safety track of AgentX (Spring ‘25) and🥈 place in the Safety track of Agents MOOC Hackathon (Fall ‘24). Thanks to @BerkeleyRDI! Credits to: PhD students @Ri7erLi, Jian Cui; faculty @xiaojingliao and myself.
Luyi Xing retweeted
Claude Cowork proves the interest in AI coworkers. Orion (meetorion.app) takes the autonomous working experience to another level:
• Works with and enhances your experience with your favorite apps (messages, docs, emails, sheets, files, calendars…) and AI tools (ChatGPT, Claude Code, Gemini, Grok…)
• Supervises workflows when you are away, from vibe coding to media creation
• Coordinates AI agents across all your devices (macOS, windows, VM), each operating one device independently
Your personal AI superpower. New surprising ways of vibe working every day - I just tried using Orion to add subtitles to the video and it worked!
Watch it handle multiple tasks autonomously from a single cmd+k.
🚀 NLIP is now a formal standard!
@EcmaIntl published the Natural Language Interaction Protocol (NLIP)—for agent-to-agent and human–agent communication across platforms and organizations.
ecma-international.org/news/…
#AgenticAI
3
179
SDIoTSec '26 @ NDSS Symposium is coming!
🚨 Explore security/privacy of emerging IoT standard and standardization (Matter, SBOM, IoT Labels & more).
🫥 Submit by Dec 10, 2025. ndss-symposium.org/ndss2026/…
@NDSSSymposium #IoT #Security #Standardization
Extending submission deadline to Dec 18th based on multiple requests.😄 ndss-symposium.org/ndss2026/…
Replying to @luyixing @NDSSSymposium
Submit papers (8 or 4 pages) by Dec. 10th and join our discussions in beautiful San Diego (February 23) to push the frontier of IoT security, standardization and compliance. ☀️ ndss-symposium.org/ndss2026/…
1
116
Extending submission deadline to Dec 18th based on multiple requests.😄 ndss-symposium.org/ndss2026/…
58
Luyi Xing retweeted
SDIoTSec '26 @ NDSS Symposium is coming!
🚨 Explore security/privacy of emerging IoT standard and standardization (Matter, SBOM, IoT Labels & more).
🫥 Submit by Dec 10, 2025. ndss-symposium.org/ndss2026/…
@NDSSSymposium #IoT #Security #Standardization
Submit IoT papers by Dec 10th (8 or 4 pages). Happy holidays! 😄 #Matter #IoT #security_labels #SBOM @NDSSSymposium
SDIoTSec '26 @ NDSS Symposium is coming!
🚨 Explore security/privacy of emerging IoT standard and standardization (Matter, SBOM, IoT Labels & more).
🫥 Submit by Dec 10, 2025. ndss-symposium.org/ndss2026/…
@NDSSSymposium #IoT #Security #Standardization
1
138
Join SaTS’25 Keynote (CCS’25)
Speaker: Dr. Mihai Christodorescu, Research Scientist @ Google
Title: Time to Deprecate Permissions? A Look at the Present and Future of Permissions
🕗 9:10 AM Mon (Taipei)
📍 Room 101A
💻 Zoom: acm-org.zoom.us/j/2581019423…
🌐 superappsec.github.io/
3
2
291
Dr. Mihai Christodorescu will discuss why today’s permission systems are collapsing under complexity and how we can reimagine data access for usability and security.
113
Luyi Xing retweeted
Join our talk to discuss improving agent security in agent frameworks/AG2, reducing security efforts/interruptions for individual agent applications. This is an award-winning approach (🥇 in AgentX safety track). Thanks to the AG2 community for inviting us and initial feedbacks!
🚨 New AG2 Talk Alert! 🚨
Join us on Aug 28, 9 AM PST for
"Maris: A Security Controlled Development Paradigm for Multi-Agent Collaboration Systems"
by @cuijian0819 Jian Cui from UIUC & Berkeley AgentX competition winner! 🛡️ #AI #Cybersecurity
RSVP now: discord.com/events/115307241…
Join our talk to discuss improving agent security in agent frameworks/AG2, reducing security efforts/interruptions for individual agent applications. This is an award-winning approach (🥇 in AgentX safety track). Thanks to the AG2 community for inviting us and initial feedbacks!
🚨 New AG2 Talk Alert! 🚨
Join us on Aug 28, 9 AM PST for
"Maris: A Security Controlled Development Paradigm for Multi-Agent Collaboration Systems"
by @cuijian0819 Jian Cui from UIUC & Berkeley AgentX competition winner! 🛡️ #AI #Cybersecurity
RSVP now: discord.com/events/115307241…
Luyi Xing retweeted
📢 The 10th Midwest Security Workshop is coming up!
🗓️ Sat, Sept 20, 2025
📍 Indiana University, Bloomington
✅ Free registration (by Aug 28)
Spread the word—please share with anyone interested!
- Website: midwestsecurityworkshop.com/
- Registration: uchicago.co1.qualtrics.com/j…
Luyi Xing retweeted
Still buzzing from the incredible #AgenticAI Summit at @UCBerkeley on 8/2 — 2,000+ joined in person, 30,000+ tuned in online. ⚡🌍
The energy was electric—visionaries, builders & researchers shaping the future of agentic AI!
Missed it? Watch the recordings:
rdi.berkeley.edu/events/agen…
Huge thanks to our speakers, sponsors, @BerkeleyRDI staff, volunteers, & everyone who joined!
This momentum builds on our 25K+ LLM Agents MOOC community—and we’re launching a new edition, Agentic AI, in the series this Sep! Sign up here: agenticai-learning.org/f25
Luyi Xing retweeted
VehicleSec 2025 is just 4 days away! It’s not too late to register. Secure your spot now.
Safe travels to those already registered, and see you in Seattle!
- usenix.org/conference/vehicl…
- Registration: usenix.org/conference/304460…
Luyi Xing retweeted
Untangling the Knot (untanglingthekn0t.com/) was nominated for Best Cryptographic Attack at the @PwnieAwards 2025.
It uncovers fundamental flaws of crypto protocols in mesh Wi-Fi systems.
Exploits and summary: untanglingthekn0t.com/
Luyi Xing retweeted
We won! congrats team! Amazing experience with the Amazon AI Challenge this year!
Meet the champions of the Amazon Nova AI Challenge, where university teams around the world went head-to-head to break and defend LLMs under real adversarial pressure:
🏆 Defending: UIUC (PurpCorn-PLAN)
🏆 Attacking: Purdue (PurCL)
🥈 CTU Prague & Nova Lisbon
These students just raised the bar for secure Gen AI.
Full recap: amzn.to/44JjrF0






















