collaborators

9 papers

cs.CR2026

Architectural Backdoors in Vision-Language Model Supply Chains via Representation Steering

Maria Rosaria Briglia, Igor Maljkovic, Antonio Emanuele Cinà +3

Vision--Language Models (VLMs) are increasingly deployed through a model supply chain in which pretrained checkpoints, architecture definitions, text encoders, and exported computa…

cs.LG2026

Steering Vectors are an Adversarial Attack Surface

Abzal Aidakhmetov, Donato Crisostomi, Tommaso Mencattini +3

Activation steering has become a popular way to control Large Language Model (LLM) behavior without fine-tuning. Since the technique is plug-and-play, users share datasets and prec…

cs.CL2026

Multi-objective Evolutionary Merging Enables Efficient Reasoning Models

Mario Iacobelli, Adrian Robert Minut, Tommaso Mencattini +5

Reasoning models achieve strong performance on complex problems by leveraging long chains of thought, but this deliberate reasoning incurs substantial inference-time cost. The Long…

cs.CR2026

Harnessing Hyperbolic Geometry for Harmful Prompt Detection and Sanitization

Igor Maljkovic, Maria Rosaria Briglia, Iacopo Masi +2

Vision-Language Models (VLMs) have become essential for tasks such as image synthesis, captioning, and retrieval by aligning textual and visual information in a shared embedding sp…

cs.LG2026

Not All Latent Spaces Are Flat: Hyperbolic Concept Control

Maria Rosaria Briglia, Simone Facchiano, Paolo Cursi +6

As modern text-to-image (T2I) models draw closer to synthesizing highly realistic content, the threat of unsafe content generation grows, and it becomes paramount to exercise contr…

cs.CV2026

A Provable Energy-Guided Test-Time Defense Boosting Adversarial Robustness of Large Vision-Language Models

Mujtaba Hussain Mirza, Antonio D'Orazio, Odelia Melamed +1

Despite the rapid progress in multimodal models and Large Visual-Language Models (LVLM), they remain highly susceptible to adversarial perturbations, raising serious concerns about…