Francesco Croce

68 papers A* 19A 1Journal 39Unranked 8

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	On the Adversarial Robustness of Discrete Image Tokenizers. CoRR Rishika Bhagwatkar, Irina Rish, Nicolas Flammarion, Francesco Croce
2026	J	`jnl`	On the Out-of-Distribution Generalization of Reasoning in Multimodal LLMs for Simple Visual Planning Tasks. CoRR Yannic Neuhaus, Nicolas Flammarion, Matthias Hein, Francesco Croce
2025	—	`conf`	Adversarially Robust CLIP Models Can Induce Better (Robust) Perceptual Metrics. SaTML Francesco Croce, Christian Schlarmann, Naman Deep Singh, Matthias Hein
2025	J	`jnl`	Adversarially Robust CLIP Models Can Induce Better (Robust) Perceptual Metrics. CoRR Francesco Croce, Christian Schlarmann, Naman Deep Singh, Matthias Hein
2025	J	`jnl`	Chain-of-Frames: Advancing Video Understanding in Multimodal LLMs via Frame-Aware Reasoning. CoRR Sara Ghazanfari, Francesco Croce, Nicolas Flammarion, Prashanth Krishnamurthy, Farshad Khorrami, Siddharth Garg
2025	J	`jnl`	FuseLIP: Multimodal Embeddings via Early Fusion of Discrete Tokens. CoRR Christian Schlarmann, Francesco Croce, Nicolas Flammarion, Matthias Hein
2025	A*	`conf`	Is In-Context Learning Sufficient for Instruction Following in LLMs? ICLR Hao Zhao, Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion
2025	A*	`conf`	Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks. ICLR Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion
2025	J	`jnl`	OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents. CoRR Thomas Kuntz, Agatha Duzan, Hao Zhao, Francesco Croce, Zico Kolter, Nicolas Flammarion, Maksym Andriushchenko
2025	J	`jnl`	Selective Induction Heads: How Transformers Select Causal Structures In Context. CoRR Francesco D'Angelo, Francesco Croce, Nicolas Flammarion
2025	A*	`conf`	Selective induction Heads: How Transformers Select Causal Structures in Context. ICLR Francesco D'Angelo, Francesco Croce, Nicolas Flammarion
2025	J	`jnl`	Unlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMs. CoRR Naman Deep Singh, Maximilian Müller, Francesco Croce, Matthias Hein
2024	J	`jnl`	Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs. CoRR Javier Rando, Francesco Croce, Krystof Mitka, Stepan Shabalin, Maksym Andriushchenko, Nicolas Flammarion, Florian Tramèr
2024	—	`—`	Evaluating and Improving the Robustness of Image Classifiers against Adversarial Attacks. Francesco Croce
2024	J	`jnl`	Is In-Context Learning Sufficient for Instruction Following in LLMs? CoRR Hao Zhao, Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion
2024	A*	`conf`	JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models. NeurIPS Patrick Chao, Edoardo Debenedetti, Alexander Robey, Maksym Andriushchenko, Francesco Croce, Vikash Sehwag, Edgar Dobriban, Nicolas Flammarion, George J. Pappas, Florian Tramèr, Hamed Hassani, Eric Wong
2024	J	`jnl`	JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models. CoRR Patrick Chao, Edoardo Debenedetti, Alexander Robey, Maksym Andriushchenko, Francesco Croce, Vikash Sehwag, Edgar Dobriban, Nicolas Flammarion, George J. Pappas, Florian Tramèr, Hamed Hassani, Eric Wong
2024	J	`jnl`	Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks. CoRR Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion
2024	A*	`conf`	Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning. ICML Hao Zhao, Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion
2024	J	`jnl`	Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning. CoRR Hao Zhao, Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion
2024	J	`jnl`	Perturb and Recover: Fine-tuning for Effective Backdoor Removal from CLIP. CoRR Naman Deep Singh, Francesco Croce, Matthias Hein
2024	A*	`conf`	Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models. ICML Christian Schlarmann, Naman Deep Singh, Francesco Croce, Matthias Hein
2024	J	`jnl`	Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models. CoRR Christian Schlarmann, Naman Deep Singh, Francesco Croce, Matthias Hein
2024	—	`conf`	Segment (Almost) Nothing: Prompt-Agnostic Adversarial Attacks on Segmentation Models. SaTML Francesco Croce, Matthias Hein
2024	—	`conf`	Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Models. ECCV (79) Francesco Croce, Naman D. Singh, Matthias Hein
2024	J	`jnl`	Towards Unified Benchmark and Models for Multi-Modal Perceptual Metrics. CoRR Sara Ghazanfari, Siddharth Garg, Nicolas Flammarion, Prashanth Krishnamurthy, Farshad Khorrami, Francesco Croce
2023	A*	`conf`	A Modern Look at the Relationship between Sharpness and Generalization. ICML Maksym Andriushchenko, Francesco Croce, Maximilian Müller, Matthias Hein, Nicolas Flammarion
2023	J	`jnl`	A modern look at the relationship between sharpness and generalization. CoRR Maksym Andriushchenko, Francesco Croce, Maximilian Müller, Matthias Hein, Nicolas Flammarion
2023	A*	`conf`	Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models. NeurIPS Naman Deep Singh, Francesco Croce, Matthias Hein
2023	J	`jnl`	Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models. CoRR Naman D. Singh, Francesco Croce, Matthias Hein
2023	A*	`conf`	Revisiting adapters with adversarial training. ICLR Sylvestre-Alvise Rebuffi, Francesco Croce, Sven Gowal
2023	J	`jnl`	Robust Semantic Segmentation: Strong Adversarial Attacks and Fast Training of Robust Models. CoRR Francesco Croce, Naman D. Singh, Matthias Hein
2023	A*	`conf`	Seasoning Model Soups for Robustness to Adversarial and Natural Distribution Shifts. CVPR Francesco Croce, Sylvestre-Alvise Rebuffi, Evan Shelhamer, Sven Gowal
2023	J	`jnl`	Seasoning Model Soups for Robustness to Adversarial and Natural Distribution Shifts. CoRR Francesco Croce, Sylvestre-Alvise Rebuffi, Evan Shelhamer, Sven Gowal
2023	J	`jnl`	Segment (Almost) Nothing: Prompt-Agnostic Adversarial Attacks on Segmentation Models. CoRR Francesco Croce, Matthias Hein
2022	A*	`conf`	Adversarial Robustness against Multiple and Single l ICML Francesco Croce, Matthias Hein
2022	A*	`conf`	Diffusion Visual Counterfactual Explanations. NeurIPS Maximilian Augustin, Valentyn Boreiko, Francesco Croce, Matthias Hein
2022	J	`jnl`	Diffusion Visual Counterfactual Explanations. CoRR Maximilian Augustin, Valentyn Boreiko, Francesco Croce, Matthias Hein
2022	A*	`conf`	Evaluating the Adversarial Robustness of Adaptive Test-time Defenses. ICML Francesco Croce, Sven Gowal, Thomas Brunner, Evan Shelhamer, Matthias Hein, A. Taylan Cemgil
2022	J	`jnl`	Evaluating the Adversarial Robustness of Adaptive Test-time Defenses. CoRR Francesco Croce, Sven Gowal, Thomas Brunner, Evan Shelhamer, Matthias Hein, A. Taylan Cemgil
2022	J	`jnl`	On the interplay of adversarial robustness and architecture components: patches, convolution and attention. CoRR Francesco Croce, Matthias Hein
2022	J	`jnl`	Revisiting adapters with adversarial training. CoRR Sylvestre-Alvise Rebuffi, Francesco Croce, Sven Gowal
2022	—	`conf`	Sparse Visual Counterfactual Explanations in Image Space. GCPR Valentyn Boreiko, Maximilian Augustin, Francesco Croce, Philipp Berens, Matthias Hein
2022	J	`jnl`	Sparse Visual Counterfactual Explanations in Image Space. CoRR Valentyn Boreiko, Maximilian Augustin, Francesco Croce, Philipp Berens, Matthias Hein
2022	A*	`conf`	Sparse-RS: A Versatile Framework for Query-Efficient Sparse Black-Box Adversarial Attacks. AAAI Francesco Croce, Maksym Andriushchenko, Naman D. Singh, Nicolas Flammarion, Matthias Hein
2021	J	`jnl`	Adversarial robustness against multiple l CoRR Francesco Croce, Matthias Hein
2021	A*	`conf`	Mind the Box: l ICML Francesco Croce, Matthias Hein
2021	J	`jnl`	Mind the box: l CoRR Francesco Croce, Matthias Hein
2021	—	`conf`	RobustBench: a standardized adversarial robustness benchmark. NeurIPS Datasets and Benchmarks Francesco Croce, Maksym Andriushchenko, Vikash Sehwag, Edoardo Debenedetti, Nicolas Flammarion, Mung Chiang, Prateek Mittal, Matthias Hein
2020	A*	`conf`	Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack. ICML Francesco Croce, Matthias Hein
2020	A*	`conf`	Provable robustness against all adversarial $l_p$-perturbations for $p\geq 1$. ICLR Francesco Croce, Matthias Hein
2020	A*	`conf`	Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks. ICML Francesco Croce, Matthias Hein
2020	J	`jnl`	Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks. CoRR Francesco Croce, Matthias Hein
2020	J	`jnl`	RobustBench: a standardized adversarial robustness benchmark. CoRR Francesco Croce, Maksym Andriushchenko, Vikash Sehwag, Nicolas Flammarion, Mung Chiang, Prateek Mittal, Matthias Hein
2020	J	`jnl`	Scaling up the Randomized Gradient-Free Adversarial Attack Reveals Overestimation of Robustness Using Established Attacks. Int. J. Comput. Vis. Francesco Croce, Jonas Rauber, Matthias Hein
2020	J	`jnl`	Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attacks. CoRR Francesco Croce, Maksym Andriushchenko, Naman D. Singh, Nicolas Flammarion, Matthias Hein
2020	—	`conf`	Square Attack: A Query-Efficient Black-Box Adversarial Attack via Random Search. ECCV (23) Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion, Matthias Hein
2019	J	`jnl`	Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack. CoRR Francesco Croce, Matthias Hein
2019	A	`conf`	Provable Robustness of ReLU networks via Maximization of Linear Regions. AISTATS Francesco Croce, Maksym Andriushchenko, Matthias Hein
2019	J	`jnl`	Provable robustness against all adversarial l CoRR Francesco Croce, Matthias Hein
2019	J	`jnl`	Scaling up the randomized gradient-free adversarial attack reveals overestimation of robustness using established attacks. CoRR Francesco Croce, Jonas Rauber, Matthias Hein
2019	A*	`conf`	Sparse and Imperceivable Adversarial Attacks. ICCV Francesco Croce, Matthias Hein
2019	J	`jnl`	Sparse and Imperceivable Adversarial Attacks. CoRR Francesco Croce, Matthias Hein
2019	J	`jnl`	Square Attack: a query-efficient black-box adversarial attack via random search. CoRR Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion, Matthias Hein
2018	—	`conf`	A Randomized Gradient-Free Attack on ReLU Networks. GCPR Francesco Croce, Matthias Hein
2018	J	`jnl`	A randomized gradient-free attack on ReLU networks. CoRR Francesco Croce, Matthias Hein
2018	J	`jnl`	Provable Robustness of ReLU networks via Maximization of Linear Regions. CoRR Francesco Croce, Maksym Andriushchenko, Matthias Hein
2001	—	`conf`	INTEGRAL Mission Control System (IMCS): Technology and Integrated Solutions for Supporting a Complex Scientific Mission. EUROMICRO Gianpiero Di Girolamo, Paolo Maldari, Francesco Croce, Michela Alberti