Xinlei He
@AllenXinleiHe
Followers
523
Following
149
Statuses
37
PhD student @CISPA working on trustworthy machine learning.
SaarbrĂĽcken, Germany
Joined September 2019
RT @realyangzhang: Excited to share TrustAIRLab! 🚀 We're dedicated to fostering Trustworthy AI with a focus on safety, privacy, and securit…
0
11
0
RT @TianshuoCong: "Stay updated on the latest works in Safety, Security, and Privacy (SSP) for Large Models (LM)!🥳" Explore our comprehensi…
0
7
0
RT @realyangzhang: @AllenXinleiHe is on the job market (mainly) for a faculty position. He is amazing () and please…
0
13
0
RT @Yiting_Qu: Nowadays, Text-to-Image models are quite popular. What if an adversary exploits such models to generate unsafe images? In ou…
0
3
0
RT @realyangzhang: We released MGTBench today for benchmarking methods on detecting whether a text is written by human or ChatGPT. Paper: h…
0
15
0
RT @realyangzhang: Happy to announce that I just got tenured at CISPA! I would like to thank all my students, collaborators, and colleagues…
0
3
0
RT @realyangzhang: Happy to announce our paper “Can’t Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders” got accepted…
0
5
0
RT @zsavvas90: Meme generation is a continuous process, with memes evolving by fusing cultural symbols. How can we study this evolutionary…
0
28
0
RT @prisec_ml: Summer is over and we are back! Next seminar Wed, September 28th, 3:30 PM (Central European Time) Prof. Tianhao Wang (@big…
0
14
0
RT @realyangzhang: Today at @USENIXSecurity, @YugengLiu will present ML-Doctor. We establish a general platform to assess ML models’ vulner…
0
10
0
RT @realyangzhang: Happy to share that our paper "Semi-Leak: Membership Inference Attacks Against Semi-supervised Learning" has just been a…
0
6
0