Francesco Croce

23 papers · 2019–2026 · 8 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

+10 more ↓

🗺️ Taxonomy Completionist (37) 🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird

👑 Triple Crown 🏆 Grand Slam 🤝 Dynamic Duo (15) 🔬 Deep Specialist (13) 🧬 Topic Evolution 🏆 Keyword Champion (2) ❓ The Questioner 🔥 Unstoppable · Bronze 💎 Century Club · Bronze 🗃️ Keyword Collector (96)

Venues

ICML (8) ICLR (5) NeurIPS (3) CVPR (2) ECCV (2) AAAI (1) AISTATS (1) ICCV (1)

Top co-authors

Matthias Hein (15) Nicolas Flammarion (9) Maksym Andriushchenko (8) Sven Gowal (3) Hao Zhao (2) Evan Shelhamer (2) Naman Deep Singh (2) Sylvestre-Alvise Rebuffi (2) Naman D. Singh (2) Prashanth Krishnamurthy (1)

Research topics

Machine Learning (17) Learning Types · Machine Learning (14) Artificial Intelligence (11) Core AI (11) Deep Learning (10) Optimization & Theory (8) Computer Vision (5) Learning Types · Deep Learning (5) Natural Language Processing (2) Analysis (2) Application Areas (2) Architectures (2) Resources & Methods (2) Techniques (2) Computer Science (1)

Keywords

adversarial robustness (9) adversarial attack (7) adversarial training (5) vision transformer (3) image classification (3) regularization scheme (2) sparse attack (2) adversarial perturbation (2) sparse perturbation (2) model soup (2) threat model (2) model robustness (2) instruction fine-tuning (2) in-context learning (2) distribution shift (2) adversarial prompt (2) large language model (2) chain-of-thought reasoning (1) attention mechanism (1) semantic segmentation (1)

Papers

Chain-of-Frames: Advancing Video Understanding in Multimodal LLMs via Frame-Aware Reasoning CVPR 2026 Is In-Context Learning Sufficient for Instruction Following in LLMs? ICLR 2025 Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks ICLR 2025 Selective Induction Heads: How Transformers Select Causal Structures in Context ICLR 2025 JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models NeurIPS 2024 Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning ICML 2024 Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models ICML 2024 Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Models ECCV 2024 A Modern Look at the Relationship between Sharpness and Generalization ICML 2023 Revisiting adapters with adversarial training ICLR 2023 Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models NeurIPS 2023 Seasoning Model Soups for Robustness to Adversarial and Natural Distribution Shifts CVPR 2023 Adversarial Robustness against Multiple and Single l_p-Threat Models via Quick Fine-Tuning of Robust Classifiers ICML 2022 Diffusion Visual Counterfactual Explanations NeurIPS 2022 Evaluating the Adversarial Robustness of Adaptive Test-time Defenses ICML 2022 Sparse-RS: A Versatile Framework for Query-Efficient Sparse Black-Box Adversarial Attacks AAAI 2022 Mind the Box: l_1-APGD for Sparse Adversarial Attacks on Image Classifiers ICML 2021 Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack ICML 2020 Provable robustness against all adversarial l_p-perturbations for p≥ 1 ICLR 2020 Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks ICML 2020 Square Attack: a query-efficient black-box adversarial attack via random search ECCV 2020 Provable Robustness of ReLU networks via Maximization of Linear Regions AISTATS 2019 Sparse and Imperceivable Adversarial Attacks ICCV 2019