2 citations · 3 across the 13 of their papers we have counts for
17 papers
Embeddings of Generalized Weighted Morrey Spaces
Zhen Liu
We study continuous embeddings from two classes of generalized weighted Morrey spaces into generalized Morrey spaces. The Komori--Shirai-type spaces use the weighted measure of cub…
Certification of Real Images through Calibrated Content Authentication
Sarim Hashmi, Abdelrahman Elsayed, Mohammed Talha Alam +2
Generative models can synthesize high-quality inauthentic multimedia content that is already being misused at scale. We evaluate twenty deepfake detectors against ten generators re…
ShieldCLIP: Selective Safety Alignment for Harmful Content Mitigation in Multimodal Foundation Models
Tobia Poppi, Silvia Cappelletti, Samuele Poppi +4
Multimodal encoders such as CLIP underlie many downstream systems, but their web-scale training data embed harmful associations that safety alignment must suppress without unnecess…
CopyShield: A Cross-Level Benchmark of Copyright Defenses in LLMs
Maryam Alshehyari, Dushyant Singh Chauhan, Samuele Poppi +3
Large language models can reproduce memorized text verbatim, yet copyright defenses are usually evaluated under incompatible protocols. We introduce CopyShield, a controlled benchm…
Context Inference Attacks Without Jailbreaks
Prince Jha, Samuele Poppi, Nils Lukas
Agentic AI systems are increasingly deployed to process sensitive data at inference time, such as healthcare records or financial documents assembled into a hidden \emph{context} b…
ReACT-CLIP: Response-Aware Test-Time Defense for Vision--Language Models
Hashmat Shadab Malik, Toluwani Aremu, Samuele Poppi +2
Training-free test-time defenses offer a practical way to improve the adversarial robustness of CLIP-style vision--language models without modifying the pretrained model. However,…
A Gravitational Interpretation of Safety Reversion under Fine-Tuning
Samuele Poppi, Nils Lukas
Safety alignment in large language models can degrade during post-training even when neither the data nor the objective is intentionally adversarial. Alignment rebound and reverse…
When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models
Sai Kartheek Reddy Kasu, Nils Lukas, Samuele Poppi
Failures in multi-turn reasoning models are largely invisible to terminal-score evaluation. A model can lock onto an unsafe stance early in a long dialogue, yet its final-turn refu…
Adaptively Robust LLM Monitoring via Activation Watermarking
Toluwani Aremu, Daniil Ognev, Samuele Poppi +1
Providers monitor deployed large language models (LLMs) to detect misuse that they cannot prevent. LLM monitoring is deterministic and often openly available, so …
Robust and Calibrated Detection of Authentic Multimedia Content
Sarim Hashmi, Abdelrahman Elsayed, Mohammed Talha Alam +2
Generative models can synthesize highly realistic content, so-called deepfakes, that are already being misused at scale to undermine digital media authenticity. Current deepfake de…
SPQR: A Multi-Dimensional Benchmark for Safety Alignment under Benign Model Adaptation
Mohammed Talha Alam, Nada Saadi, Fahad Shamshad +4
Text-to-image diffusion models can emit copyrighted, unsafe, or private content. Safety alignment aims to suppress specific concepts, yet evaluations seldom test whether safety per…
Mitigating Watermark Forgery in Generative Models via Randomized Key Selection
Toluwani Aremu, Noor Hussein, Munachiso Nwadike +5
Watermarking enables GenAI providers to verify whether content was generated by their models. A watermark is a hidden signal in the content, whose presence can be detected using a…
Improving LLM First-Token Predictions in Multiple-Choice Question Answering via Output Prefilling
Silvia Cappelletti, Tobia Poppi, Samuele Poppi +5
Large Language Models (LLMs) are increasingly evaluated on multiple-choice question answering (MCQA) tasks using *first-token probability* (FTP), which selects the answer option wh…
Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks
Samuele Poppi, Zheng-Xin Yong, Yifei He +4
Recent advancements in Large Language Models (LLMs) have sparked widespread concerns about their safety. Recent work demonstrates that safety alignment of LLMs can be easily remove…
Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models
Samuele Poppi, Tobia Poppi, Federico Cocchi +3
Large-scale vision-and-language models, such as CLIP, are typically trained on web-scale data, which can introduce inappropriate content and lead to the development of unsafe and b…
Multi-Class Unlearning for Image Classification via Weight Filtering
Samuele Poppi, Sara Sarto, Marcella Cornia +2
Machine Unlearning is an emerging paradigm for selectively removing the impact of training datapoints from a network. Unlike existing methods that target a limited subset or a sing…
Revisiting The Evaluation of Class Activation Mapping for Explainability: A Novel Metric and Experimental Analysis
Samuele Poppi, Marcella Cornia, Lorenzo Baraldi +1
As the request for deep learning solutions increases, the need for explainability is even more fundamental. In this setting, particular attention has been given to visualization te…