← Authors

Francesco Croce

22 papers · 2019–2025 · 8 conferences · across top CS/AI conferences

Achievements

🌈 Renaissance Researcher (6) 🌍 Conference Polyglot (8) πŸƒ Academic Marathon (6) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (10) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (12) 🀝 Dynamic Duo (15) πŸ‘‘ Triple Crown πŸ† Grand Slam πŸ† Keyword Champion (2) πŸ’Ž Century Club (22) ❓ The Questioner πŸ—ƒοΈ Keyword Collector (59) πŸ”₯ Unstoppable (7)

Conferences

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

Top co-authors

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

Keywords

adversarial robustness (8) adversarial attack (6) adversarial training (3) vision transformer (2) sparse perturbation (2) image classification (2) sparse attack (2) threat model (2) model robustness (2) black-box optimization (1) efficient computing (1) neural network optimization (1) out-of-distribution generalization (1) ai safety (1) image generation (1) adversarial learning (1) black-box attack (1) query efficiency (1) projected gradient descent (1) random search (1)

Papers

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