Get started
Author

Samuele Poppi

Observed names: POPPI, SAMUELE, Poppi, Samuele
ORCID: 0000-0002-8428-501X
Observed ORCID: 0000-0002-8428-501X
OpenAlex ID: A5011288168
Revisiting The Evaluation of Class Activation Mapping for Explainability: A Novel Metric and Experimental Analysis
2021 · Samuele Poppi, Marcella Cornia, et al. · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · 67
PDF
Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models
2024 · Samuele Poppi, Tobia Poppi, et al. · Lecture notes in computer science · 20
PDF
Unveiling the Impact of Image Transformations on Deepfake Detection: An Experimental Analysis
2023 · Federico Cocchi, Lorenzo Baraldi, et al. · Lecture notes in computer science · 15
PDF
Multiclass Unlearning for Image Classification via Weight Filtering
2024 · Samuele Poppi, Sara Sarto, et al. · IEEE Intelligent Systems · 14
PDF
Unlearning Vision Transformers Without Retaining Data via Low-Rank Decompositions
2024 · Samuele Poppi, Sara Sarto, et al. · Lecture notes in computer science · 4
PDF
Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks
2025 · Samuele Poppi, Zheng Xin Yong, et al. · Findings of the Association for Computational Linguistics: NAACL · 3
PDF
Tricking Synthetic Image Detectors with Amortized Generative Attacks
2026 · Awad, Mohamed, Elhady, Khaled, et al. · arXiv (Cornell University)
PDF
Constitution-Guided Watermarking
2026 · Aremu, Toluwani, Poppi, Samuele, et al. · arXiv (Cornell University)
PDF
Certification of Real Images through Calibrated Content Authentication
2026 · Hashmi, Sarim, Elsayed, Abdelrahman, et al. · arXiv (Cornell University)
PDF
ShieldCLIP: Selective Safety Alignment for Harmful Content Mitigation in Multimodal Foundation Models
2026 · Poppi, Tobia, Cappelletti, Silvia, et al. · arXiv (Cornell University)
PDF
Context Inference Attacks Without Jailbreaks
2026 · Jha, Prince, Poppi, Samuele, et al. · arXiv (Cornell University)
PDF
Improving LLM First-Token Predictions in Multiple-Choice Question Answering via Output Prefilling
2026 · Silvia Cappelletti, Tobia Poppi, et al. · Lecture notes in computer science
PDF
ReACT-CLIP: Response-Aware Test-Time Defense for Vision--Language Models
2026 · Malik, Hashmat Shadab, Aremu, Toluwani, et al. · arXiv (Cornell University)
PDF
A Gravitational Interpretation of Safety Reversion under Fine-Tuning
2026 · Poppi, Samuele, Lukas, Nils · arXiv (Cornell University)
PDF
When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models
2026 · Kasu, Sai Kartheek Reddy, Lukas, Nils, et al. · arXiv (Cornell University)
PDF
Adaptively Robust LLM Monitoring via Activation Watermarking
2026 · Aremu, Toluwani, Ognev, Daniil, et al. · arXiv (Cornell University)
PDF
SPQR: A Multi-dimensional Benchmark for Safety Alignment Under Benign Model Adaptation
2026 · Mohammed Talha Alam, Nada Saadi, et al. · Lecture notes in computer science
PDF
CopyShield: A Cross-Level Benchmark of Copyright Defenses in LLMs
2026 · Maryam Alshehyari, Dushyant Singh Chauhan, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Mitigating Watermark Forgery in Generative Models via Randomized Key Selection
2025 · Aremu, Toluwani, Hussein, Noor, et al. · arXiv (Cornell University)
PDF
Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models
2023 · Poppi, Samuele, Poppi, Tobia, et al. · arXiv (Cornell University)
PDF
Towards Explainable Navigation and Recounting
2023 · Samuele Poppi, Roberto Bigazzi, et al. · Lecture notes in computer science
PDF
Works count: 25
Citation count: 123
H-index: 4
I10-index: 4
Year
Topic
Type