happy to share that my former student @zhenglisec has won ERCIM WG STM Best Ph.D. Thesis Award 2024! Zheng has published several interesting papers in the field of ML privacy during his phd, I’m looking forward to more cool works from him in the future!
Facing off in the AI arena: LoRA, Soft Prompt Tuning & In-Context Learning! Our latest paper 'Last One Standing' compares these fine-tuning techniques against the dark arts of membership inference, model stealing, & backdoor attacks. 🤖🛡️
paper: https://t.co/Ialu9OyvQJ
@AllenXinleiHe is on the job market (mainly) for a faculty position. He is amazing (https://t.co/BV5rGSP7Ut ) and please do consider him if your institutions are hiring in the field of trustworthy machine learning!
Today at @USENIXSecurity, @YugengLiu 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: https://t.co/vfOVOFXPoT Code: https://t.co/U7YUi6YXsM
On Thursday, @AllenXinleiHe will present our work at @USENIXSecurity (#usesec21). In this paper, we perform the first link stealing attacks against transductive GNNs. Paper: https://t.co/cLzmwtJ5jh Code: https://t.co/2sXk7Zm69g
@CISPA@NeilGong
Happy to announce that our paper "Membership Leakage in Label-Only Exposures" got accepted to #CCS21#CCS2021@acm_ccs. Big congratulations to @zhenglisec for his first paper as a PhD student. @CISPA
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! https://t.co/DGu2jeVCK7