📢 Check out our new report: we show that a recently proposed defense against adversarial attacks is not robust. We circumvent gradient masking issues of the proposed model by attacking a slightly adapted surrogate model and then transferring the perturbations.
speaking of: Nneka is currently on the job market for a postdoc position in north america, preferably canada. do reach out to her (or me) if you know of anything or are looking for someone to do cool work on RL (theory)
*PLS SHARE*
Open position for an *Associate Professor* in Machine Learning at our department (@enginyeria-upf.bsky.social / @upf.edu), via the Serra Hunter programme.
DEADLINE: January 13th 2025
www.upf.edu/web/personal...
Are you interested in data contamination and LLM benchmarks?🤖
Check out our poster today at the NeurIPS ATTRIB workshop (3-4:30pm)!
💡 TL;DR: In the large-data regime, a few times of data contamination matter less than you might think.
I'd like to be added, too :)
