Maffeis, Sergio

1. HarmLevelBench: Evaluating Harm-Level Compliance and the Impact of Quantization on Model Alignment
   2024/11/11 by Yannis Belkhiter, Giulio Zizzo, Belkhiter, Yannis +3 · 2 citations
   Medicine · #HIV, Drug Use, Sexual Risk
2. Certified Federated Adversarial Training
   2021/12/20 by Zizzo, Giulio, Rawat, Ambrish, Sinn, Mathieu +2 · 1 citation
   #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG)
3. Helping LLMs Improve Code Generation Using Feedback from Testing and Static Analysis
   2024/12/19 by Dolcetti, Greta, Arceri, Vincenzo, Iotti, Eleonora +3 · 2 citations
   #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Software Engineering (cs.SE)
4. Elevating Defenses: Bridging Adversarial Training and Watermarking for Model Resilience
   2023/12/21 by Thakkar, Janvi, Zizzo, Giulio, Maffeis, Sergio · 1 citation
   #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG)