Francesco Croce

发表

Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attacks

Naman D. Singh, Nicolas Flammarion, Matthias Hein, 2020, ArXiv.

RobustBench: a standardized adversarial robustness benchmark

Nicolas Flammarion, Prateek Mittal, Matthias Hein, 2020, NeurIPS Datasets and Benchmarks.

Adversarial Robustness against Multiple and Single lp-Threat Models via Quick Fine-Tuning of Robust Classifiers

Matthias Hein, Francesco Croce, 2021, ICML.

Evaluating the Adversarial Robustness of Adaptive Test-time Defenses

Evan Shelhamer, Matthias Hein, A. Cemgil, 2022, ICML.

Revisiting adapters with adversarial training

Sven Gowal, Francesco Croce, Sylvestre-Alvise Rebuffi, 2022, ICLR.

Sparse Visual Counterfactual Explanations in Image Space

Philipp Berens, Matthias Hein, Francesco Croce, 2022, GCPR.

Diffusion Visual Counterfactual Explanations

Matthias Hein, Francesco Croce, Maximilian Augustin, 2022, NeurIPS.

On the interplay of adversarial robustness and architecture components: patches, convolution and attention

Matthias Hein, Francesco Croce, 2022, ArXiv.

Scaling up the Randomized Gradient-Free Adversarial Attack Reveals Overestimation of Robustness Using Established Attacks

Matthias Hein, Jonas Rauber, Francesco Croce, 2019, International Journal of Computer Vision.

Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks

Matthias Hein, Francesco Croce, Matthias Hein, 2020, ICML.

Provable Robustness of ReLU networks via Maximization of Linear Regions pdf

Matthias Hein, Francesco Croce, Maksym Andriushchenko, 2018, AISTATS.

Provable robustness against all adversarial lp-perturbations for p≥1 pdf

Matthias Hein, Francesco Croce, Matthias Hein, 2019, ICLR.

Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack

Matthias Hein, Francesco Croce, Matthias Hein, 2019, ICML.

Square Attack: a query-efficient black-box adversarial attack via random search

Nicolas Flammarion, Matthias Hein, Maksym Andriushchenko, 2019, ECCV.

Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attacks pdf

Nicolas Flammarion, Matthias Hein, Francesco Croce, 2020, AAAI.

Sparse and Imperceivable Adversarial Attacks

Matthias Hein, Francesco Croce, Matthias Hein, 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models

Naman D. Singh, Matthias Hein, Francesco Croce, 2023, ArXiv.

A modern look at the relationship between sharpness and generalization

Nicolas Flammarion, Matthias Hein, Maksym Andriushchenko, 2023, ICML.

Mind the box: l1-APGD for sparse adversarial attacks on image classifiers

Matthias Hein, Francesco Croce, 2021, ICML.

Seasoning Model Soups for Robustness to Adversarial and Natural Distribution Shifts

Evan Shelhamer, Sven Gowal, Francesco Croce, 2023, arXiv.org.

Robust Semantic Segmentation: Strong Adversarial Attacks and Fast Training of Robust Models

Naman D. Singh, Matthias Hein, Francesco Croce, 2023, arXiv.org.

A randomized gradient-free attack on ReLU networks

Matthias Hein, Francesco Croce, Matthias Hein, 2018, GCPR.

Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models

Naman D. Singh, Matthias Hein, Francesco Croce, 2023, ArXiv.

Provable robustness against all adversarial $l_p$-perturbations for $p\geq 1$

Francesco Croce, Matthias Hein, Matthias Hein, 2019, ICLR.

Beyond Performance: Quantifying and Mitigating Label Bias in LLMs

Kuntal Kumar Pal, Shailaja Keyur Sampat, Maksym Andriushchenko, 2024, NAACL.

Segment (Almost) Nothing: Prompt-Agnostic Adversarial Attacks on Segmentation Models

Francesco Croce, Matthias Hein, 2023, 2024 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML).