Francesco Croce

6

Papers

409

Total Citations

Papers (6)

Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents

NeurIPS 2025arXiv

Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Models

Selective induction Heads: How Transformers Select Causal Structures in Context

Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models

Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning