Publications

Samuele Poppi, Nils Lukas . A Gravitational Interpretation of Fine-Tuning Reversion. In arXiv 2026.

Sai Kartheek Reddy Kasu, Nils Lukas, Samuele Poppi . When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models. In arXiv 2026.

Mohammed Talha Alam, Nada Saadi, Fahad Shamshad, Nils Lukas, Karthik Nandakumar, Fakhri Karray, Samuele Poppi . SPQR: A Multi-Dimensional Benchmark for Safety Alignment under Benign Model Adaptation. In ECCV 2026.

Toluwani Aremu, Daniil Ognev, Samuele Poppi, Nils Lukas . Robust Safety Monitoring of Language Models via Activation Watermarking. In arXiv 2026.

Silvia Cappelletti, Tobia Poppi, Samuele Poppi, Zheng-Xin Yong, Diego Garcia-Olano, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara . Improving LLM First-Token Predictions in Multiple-Choice Question Answering via Output Prefilling. In ICPR 2026.

Sarim Hashmi, Abdelrahman Elsayed, Mohammed Talha Alam, Samuele Poppi, Nils Lukas . Robust and Calibrated Detection of Authentic Multimedia Content. In arXiv 2025.

Toluwani Aremu, Noor Hussein, Munachiso Nwadike, Samuele Poppi, Jie Zhang, Karthik Nandakumar, Neil Gong, Nils Lukas . Mitigating Watermark Forgery in Generative Models via Randomized Key Selection. In arXiv 2025.

Samuele Poppi, Sara Sarto, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara . Unlearning Vision Transformers without Retaining Data via Low-Rank Decompositions. In ICPR 2024.

Samuele Poppi, Zheng-Xin Yong, Yifei He, Bobbie Chern, Han Zhao, Aobo Yang, Jianfeng Chi . Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks. In NAACL 2025.

Samuele Poppi, Sara Sarto, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara . Multiclass Unlearning for Image Classification via Weight Filtering. In IEEE Intelligent Systems 2024.