3

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs
Jailbreak attacks exploit specific prompts to bypass LLM safeguards, causing the LLM to generate harmful, inappropriate, and misaligned …
arXiv
Optimization and optimizers for adversarial robustness
Empirical evaluation of deep learning models against adversarial perturbations entails solving nontrivial constrained optimization …
arXiv
Using Neural Networks to Predict Radiation Damage to Lead Tungstate Crystals at the CERN LHC
The 72,000 lead tungstate crystals in CMS experiment at the CERN Large Hadron Collider are used to measure the energy of electrons and …
Last updated on Jul 247, 242424
Paper Website
NCVX: A User-Friendly and Scalable Package for Nonconvex Optimization in Machine Learning
Optimizing nonconvex (NCVX) problems, especially nonsmooth and constrained ones, is an essential part of machine learning. However, it …
arXiv