Raymond

PhD student @CISPA; Formerly @GeorgiaTech; NLP; Security & Privacy; 🇲🇴

[Yang Zhang @realyangzhang]

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 ➡️ https://t.co/lBPBJNvKg3

[Yang Zhang @realyangzhang]

Happy to announce that our paper "Two-in-One: A Model Hijacking Attack Against Text Generation Models" just got accepted to USENIX Security 2023 @USENIXSecurity Kudos to @RaymondSi4 and @AhmedGaSalem! @CISPA

[Yang Zhang @realyangzhang]

Happy to share that our paper "Why So Toxic? Measuring and Triggering Toxic Behavior in Open-Domain Chatbots" got the best paper honorable mention at @acm_ccs, this is a great collaboration and team effort between @iDRAMALab and @CISPA.

[Yang Zhang @realyangzhang]

Happy to share our paper led by @RaymondSi4 “Why So Toxic? Measuring and Triggering Toxic Behavior in Open-Domain Chatbots” (https://t.co/RSBzK4pdGi) is accepted by @acm_ccs, this is a great collaboration and #teameffort @emilianoucl @jhblackb @zsavvas90 @gianluca_string @CISPA

[prisec_ml @prisec_ml]

Summer is over and we are back!

Next seminar Wed, September 28th, 3:30 PM (Central European Time)

Prof. Tianhao Wang (@bigflywth, University of Virginia)

"Continuous Release of Data Streams under Differential Privacy"

Details: https://t.co/OaiQcSrTNV