Amazing🙃🙃🙃

每天这个点醒了，就很饿，但也不敢出门

就在我家附近😅 baltimore.cbslocal.com/2019/07/04/tee…

I have placed the order

✌🏻

🤔

😭😭😭😭😭😭 tmz.com/2020/01/26/kob…

I'm looking for multiple Ph.D. students and postdocs to work on machine learning security and privacy at CISPA Helmholtz Center for Information Security, Germany. @CISPA Apply by December 1st, 2021! yangzhangalmo.github.io/hiring/

Using 1.9 billion if loops to check the item hash values nee.lv/2021/02/28/How…

On Thursday, Xinlei He will present our work at USENIX Security (#usesec21). In this paper, we perform the first link stealing attacks against transductive GNNs. Paper: arxiv.org/abs/2005.02131 Code: github.com/xinleihe/link_… @CISPA Neil Gong

Welcome to submit your awesome papers on ethics and security to the workshop! @CISPA

Today at USENIX Security, Yug3n9 will present ML-Doctor. We establish a general platform to assess ML models’ vulnerabilities wrt 4 inference attacks and analyze the synergy between these attacks. Paper: arxiv.org/abs/2102.02551 Code: github.com/liuyugeng/ML-D…

Casemiro to Man United, here we go! Real Madrid accepted all details of the bid, clubs preparing contracts right now. €60m fixed fee, €10m add-ons 🚨🔴🇧🇷 #MUFC Casemiro has full agreement on four year deal, option until 2027. Medical and then visa to be sorted during weekend.

Summer is over and we are back! Next seminar Wed, September 28th, 3:30 PM (Central European Time) Prof. Tianhao Wang (Tianhao Wang, University of Virginia) "Continuous Release of Data Streams under Differential Privacy" Details: prisec-ml.github.io

If you are at ACM CCS 2025 today, welcome to join the talk of Zheng Li!

Xinlei He is on the job market (mainly) for a faculty position. He is amazing (xinleihe.github.io ) and please do consider him if your institutions are hiring in the field of trustworthy machine learning!

"Stay updated on the latest works in Safety, Security, and Privacy (SSP) for Large Models (LM)!🥳" Explore our comprehensive reading list, LM-SSP, co-organized with Xinlei He, Zhengyu Zhao (赵正宇), & Yug3n9. 🔗github.com/ThuCCSLab/lm-s… 🆕LM-SSP adds 107 papers from #ICLR2024!

Excited to share TrustAIRLab! 🚀 We're dedicated to fostering Trustworthy AI with a focus on safety, privacy, and security. Dive into our libraries for easier algorithm reproduction, benchmarks for ML model attacks & defenses, and more. Check it out ➡️ github.com/TrustAIRLab

🚀Just updated: We present our longitudinal robustness tests on LLaMA (v1, v2, v2 Chat, v3, and v3 Instruct), GPT-3.5 (v0613, v1106, and v0125), and GPT-4 (v0613, v1106, v0125, and v0409) across three critical categories: misclassification, jailbreak, and hallucination!