Giulio Zizzo

Researcher, International Business Machines

Joined

September 2022

Names

Giulio Zizzo (Preferred)

Emails

****@ibm.com (Confirmed)

Personal Links

Google Scholar

DBLP

Career & Education History

Researcher

International Business Machines (ibm.com)

2021 – Present

PhD student

Imperial College London (ic.ac.uk)

2017 – 2021

Advisors, Relations & Conflicts

No relations added

Expertise

Machine Learning

2017 – Present

Publications

Breaking MCP with Function Hijacking Attacks: Novel Threats for Function Calling and Agentic Models
Yannis Belkhiter, Giulio Zizzo, Sergio Maffeis, Seshu Tirupathi, John D. Kelleher
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Step-Tagging: Toward controlling the generation of Language Reasoning Models through step monitoring
Yannis Belkhiter, Seshu Tirupathi, Giulio Zizzo, John D. Kelleher
- Submitted to ICLR 2026
- Readers: Everyone
Dynamic Features Adaptation in Networking: Toward Flexible training and Explainable inference
Yannis Belkhiter, Seshu Tirupathi, Giulio Zizzo, Merim Dzaferagic, John Kelleher
- AI4NextG @ NeurIPS 25 Poster
- Readers: Everyone
SIVA: Self-Improving Vulnerability Agent
Valentin Walischewski, Giulio Zizzo, Kevin N. Webster
- NeurIPS 2025 - Reliable ML Workshop
- Readers: Everyone
MAD-MAX: Modular And Diverse Malicious Attack MiXtures for Automated LLM Red Teaming
Stefan Schoepf, Muhammad Zaid Hameed, Ambrish Rawat, Kieran Fraser, Giulio Zizzo, Giandomenico Cornacchia, Mark Purcell
- DIG-BUG Long
- Readers: Everyone
Activated LoRA: Fine-tuned LLMs for Intrinsics
Kristjan Greenewald, Luis A. Lastras, Thomas Parnell, Vraj Shah, Lucian Popa, Giulio Zizzo, Chulaka Gunasekara, Ambrish Rawat, David Daniel Cox
- NeurIPS 2025 poster
- Readers: Everyone
Granite Guardian
Inkit Padhi, Manish Nagireddy, Giandomenico Cornacchia, Subhajit Chaudhury, Tejaswini Pedapati, Pierre Dognin, Keerthiram Murugesan, Erik Miehling, Martín Santillán Cooper, Kieran Fraser, Giulio Zizzo, Muhammad Zaid Hameed, Mark Purcell, Michael Desmond, Qian Pan, Zahra Ashktorab, Inge Vejsbjerg, Elizabeth M. Daly, Michael Hind, Werner Geyer et al. (3 additional authors not shown)
- OpenReview Archive Direct Upload
- Readers: Everyone
MED: Exploring LLM Memorization of Encrypted Data
Panagiotis Christodoulou, Giulio Zizzo, Sergio Maffeis
- SafeGenAi Poster
- Readers: Everyone
HarmLevelBench: Evaluating Harm-Level Compliance and the Impact of Quantization on Model Alignment
Yannis Belkhiter, Giulio Zizzo, Sergio Maffeis
- SafeGenAi Poster
- Readers: Everyone
Adversarial Prompt Evaluation: Systematic Benchmarking of Guardrails Against Prompt Input Attacks on LLMs
Giulio Zizzo, Giandomenico Cornacchia, Kieran Fraser, Muhammad Zaid Hameed, Ambrish Rawat, Beat Buesser, Mark Purcell, Pin-Yu Chen, Prasanna Sattigeri, Kush R. Varshney
- SafeGenAi Oral
- Readers: Everyone

View all 40 publications

Co-Authors

View all 81 co-authors