Jian Cui

52 posts

Jian Cui

Jian Cui

@cuijian0819

Ph.D. student at UIUC | LLM Agent & Data-Driven Security | Former Intern @AmazonScience, @S2W_Official | KAIST alumni | Opinions are from my training data.

Illinois, United States Katılım Aralık 2017
382 Takip Edilen74 Takipçiler
Sabitlenmiş Tweet
Jian Cui
Jian Cui@cuijian0819·
@Ri7erLi and I will present our paper "Les Dissonances: Cross-Tool Harvesting and Polluting in Pool-of-Tools Empowered LLM Agents" at NDSS. Location: Coast Ballroom (Session 3B Time: 14:30–15:50 Come by if you're around, happy to chat! 🙌 Paper: ndss-symposium.org/wp-content/upl…
Jian Cui tweet media
English
3
1
2
186
Jian Cui retweetledi
Boris Cherny
Boris Cherny@bcherny·
I wanted to share a bunch of my favorite hidden and under-utilized features in Claude Code. I'll focus on the ones I use the most. Here goes.
English
554
2.5K
23.2K
3.9M
Jian Cui retweetledi
Noah
Noah@NoahKingJr·
Claude watching me write code manually after I hit the daily limit
English
402
5.9K
80.9K
3.7M
Jian Cui retweetledi
Om Patel
Om Patel@om_patel5·
stop spending money on Claude Code. Chipotle's support bot is free:
Om Patel tweet media
English
1.2K
10.1K
159.5K
7.9M
Jian Cui
Jian Cui@cuijian0819·
@Ri7erLi We also develop a threat scanner, Chord, and find that 75% of 66 real tools from LangChain and Llama-Index are vulnerable. XTHP is not limited to the tool ecosystems we evaluated. Emerging tool-calling paradigms such as MCP and Skills are also vulnerable to our XTHP attack!
English
0
0
0
19
Jian Cui
Jian Cui@cuijian0819·
@Ri7erLi and I will present our paper "Les Dissonances: Cross-Tool Harvesting and Polluting in Pool-of-Tools Empowered LLM Agents" at NDSS. Location: Coast Ballroom (Session 3B Time: 14:30–15:50 Come by if you're around, happy to chat! 🙌 Paper: ndss-symposium.org/wp-content/upl…
Jian Cui tweet media
English
3
1
2
186
Jian Cui
Jian Cui@cuijian0819·
@Ri7erLi 🟠 Cross-Tool Data Harvesting: Once embedded, it can harvest arbitrary sensitive data within the context. 🟡 Cross-Tool Information Polluting: Or it can silently pollute the agent context, return incorrect or misleading outputs that affect agent decisions.
English
0
0
0
18
Jian Cui
Jian Cui@cuijian0819·
@Ri7erLi In our paper, we identify a novel threat named Cross-Tool Harvesting and Polluting (XTHP): 🔴 Control-Flow Hijacking: A malicious tool can manipulate the tool descriptions to hijack the agent’s control flow, inserting itself before or after legitimate tools.
English
0
0
0
16
Jian Cui retweetledi
Netflix
Netflix@netflix·
ALEX HONNOLD AFTER COMPLETING HIS FREE SOLO OF TAIPEI 101: "Sick." The 101 story climb took 1 hour and 35 minutes #SkyscraperLIVE
English
1.5K
7.7K
59.9K
20.9M
Jian Cui retweetledi
Ruikai Peng
Ruikai Peng@ruikai·
This is my story, of a "hacker" kiddo who always wanted to become a comedian before watching a TV show. I wrote this to prepare my interview with bloomberg but it seems like they only talked a little part of it. Try to ignore the grammar issue hahaha! dull-buckaroo-11a.notion.site/My-story-2a523…
English
0
2
12
2.2K
Jian Cui retweetledi
Chi Wang
Chi Wang@Chi_Wang_·
🚨 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/1153072…
Chi Wang tweet media
English
2
5
22
2.6K
alphaXiv
alphaXiv@askalphaxiv·
Introducing GPT OSS for understanding research papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references
English
5
97
560
29.5K
Jian Cui
Jian Cui@cuijian0819·
Had a wonderful time at @BerkeleyRDI Agentic AI Summit! Our Team Hoosiers took the 1st place in AgentX AI Safety track (25’Spring) and 2nd place in MOOC Hackathon Safety track (24’Fall)! Huge shoutout to my teammate @Ri7erLi and our bosses @xiaojingliao and @luyixing!!
Jian Cui tweet mediaJian Cui tweet mediaJian Cui tweet media
English
0
0
6
202
Jian Cui retweetledi
Luyi Xing
Luyi Xing@luyixing·
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 tweet mediaLuyi Xing tweet media
English
0
2
14
1.2K
Jian Cui retweetledi
Mckay Wrigley
Mckay Wrigley@mckaywrigley·
So I gave Claude Code a Mac Mini. And it’s called Claudeputer. It runs 24/7 and it’s allowed to do whatever it wants - it’s in complete control of its computer. Watch for a 2min demo.
English
641
768
9.9K
3M
Jian Cui retweetledi
Stijn Spanhove
Stijn Spanhove@stspanho·
🚫🕶️ I've been building an XR app for a real-world ad blocker using Snap @Spectacles. It uses Gemini to detect and block ads in the environment. It’s still early and experimental, but it’s exciting to imagine a future where you control the physical content you see.
English
250
394
3.7K
349.4K
Jian Cui retweetledi
XBOW
XBOW@Xbow·
For the first time in history, the #1 hacker in the US is an AI. (1/8)
English
39
142
675
264.7K
Jian Cui retweetledi
Andy Zhou
Andy Zhou@zhouandy_·
Announcing the first fully AI-generated scientific discovery to pass the highest level of peer review – the main track of an A* conference (ACL 2025). Several groups have shown AI-generated work at workshops, but main conference acceptance is a far higher bar. While workshops often accept more than 50% of submissions, top-tier venues like ACL accept ~20%.
English
19
28
256
71.1K