Croce, Francesco
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
2024/04/02 by Maksym Andriushchenko, Francesco Croce, Andriushchenko, Maksym +3 · 4 voices · 93 citations
Computer Science · Engineering · Mathematics · #Artificial Intelligence (cs.AI) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Information and Cyber Security #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Safety Systems Engineering in Autonomy #cs.AI #cs.CR #cs.LG #stat.ML
- Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks
2020/03/03 by Francesco Croce, Croce, Francesco, Matthias Hein +1 · 106 citations
Computer Science · Biochemistry, Genetics and Molecular Biology · Engineering · #Adversarial Robustness in Machine Learning #Bacillus and Francisella bacterial research #Integrated Circuits and Semiconductor Failure Analysis
- Square Attack: a query-efficient black-box adversarial attack via random search
2019/11/29 by Andriushchenko, Maksym, Croce, Francesco, Flammarion, Nicolas +1 · 59 citations
#Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- RobustBench: a standardized adversarial robustness benchmark
2020/10/19 by Francesco Croce, Maksym Andriushchenko, Croce, Francesco +13 · 53 citations
Computer Science · Medicine · #Adversarial Robustness in Machine Learning #Cardiac Arrest and Resuscitation #Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
2024/03/28 by Patrick Chao, Edoardo Debenedetti, Chao, Patrick +21 · 99 citations
Computer Science · #Authorship Attribution and Profiling #Cryptography and Security (cs.CR) #Digital and Cyber Forensics #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques
- Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning
2024/02/07 by Hao Zhao, Maksym Andriushchenko, Zhao, Hao +5 · 2 voices · 18 citations
Computer Science · Engineering · #Computation and Language (cs.CL) #Experimental Learning in Engineering #FOS: Computer and information sciences #cs.CL
- Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack
2019/07/03 by Francesco Croce, Croce, Francesco, Matthias Hein +1 · 19 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Engineering · #Adversarial Robustness in Machine Learning #Bacillus and Francisella bacterial research #Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Integrated Circuits and Semiconductor Failure Analysis #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models
2024/02/19 by Schlarmann, Christian, Singh, Naman Deep, Croce, Francesco +1 · 26 citations
#Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- A Modern Look at the Relationship between Sharpness and Generalization
2023/02/14 by Maksym Andriushchenko, Andriushchenko, Maksym, Francesco Croce +7 · 16 citations
Computer Science · Engineering · #FOS: Computer and information sciences #Image Processing Techniques and Applications #Industrial Vision Systems and Defect Detection #Machine Learning (cs.LG) #Optical measurement and interference techniques
- Diffusion Visual Counterfactual Explanations
2022/10/21 by Maximilian Augustin, Valentyn Boreiko, Augustin, Maximilian +5 · 13 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Cell Image Analysis Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models
2023/03/03 by Naman D Singh, Francesco Croce, Singh, Naman D +3 · 10 citations
Computer Science · Medicine · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #COVID-19 diagnosis using AI #Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Sparse and Imperceivable Adversarial Attacks
2019/09/11 by Croce, Francesco, Hein, Matthias · 5 citations
#Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attacks
2020/06/23 by Croce, Francesco, Andriushchenko, Maksym, Singh, Naman D. +2 · 5 citations
#Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- Adversarial Robustness against Multiple and Single lp-Threat Models via Quick Fine-Tuning of Robust Classifiers
2021/05/26 by Croce, Francesco, Hein, Matthias · 5 citations
#Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Mind the box: l1-APGD for sparse adversarial attacks on image classifiers
2021/03/01 by Croce, Francesco, Hein, Matthias · 4 citations
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Evaluating the Adversarial Robustness of Adaptive Test-time Defenses
2022/02/28 by Francesco Croce, Croce, Francesco, Sven Gowal +8 · 4 citations
Computer Science · Medicine · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Medical Imaging Techniques and Applications
- OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents
2025/06/17 by Kuntz, Thomas, Duzan, Agatha, Zhao, Hao +4 · 14 citations
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Software Engineering (cs.SE)
- Chain-of-Frames: Advancing Video Understanding in Multimodal LLMs via Frame-Aware Reasoning
2025/05/31 by Sara Ghazanfari, Ghazanfari, Sara, Francesco Croce +9 · 10 citations
Computer Science · #Multimodal Machine Learning Applications #Video Analysis and Summarization #Natural Language Processing Techniques
- Is In-Context Learning Sufficient for Instruction Following in LLMs?
2024/05/30 by Hao Zhao, Maksym Andriushchenko, Zhao, Hao +5 · 1 voice · 1 citation
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #cs.AI #cs.CL #cs.LG
- Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs
2024/04/22 by Javier Rando, Rando, Javier, Francesco Croce +11 · 4 citations
Computer Science · Economics, Econometrics and Finance · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Law, AI, and Intellectual Property #Law, Economics, and Judicial Systems #Machine Learning (cs.LG)
- Seasoning Model Soups for Robustness to Adversarial and Natural Distribution Shifts
2023/02/20 by Croce, Francesco, Rebuffi, Sylvestre-Alvise, Shelhamer, Evan +1 · 2 citations
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Provable Robustness of ReLU networks via Maximization of Linear Regions
2018/10/17 by Croce, Francesco, Andriushchenko, Maksym, Hein, Matthias · 1 citation
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- A randomized gradient-free attack on ReLU networks
2018/11/28 by Croce, Francesco, Hein, Matthias · 1 citation
#Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- Scaling up the randomized gradient-free adversarial attack reveals\n overestimation of robustness using established attacks
2019/03/27 by Francesco Croce, Croce, Francesco, Jonas Rauber +3 · 1 citation
Computer Science · Materials Science · #Adversarial Robustness in Machine Learning #Machine Learning in Materials Science #Advanced Neural Network Applications
- Unlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMs
2025/09/02 by Naman Deep Singh, Singh, Naman Deep, Maximilian Müller +5 · 6 citations
Computer Science · #Adversarial Robustness in Machine Learning #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Topic Modeling
- Evaluating the Robustness of the "Ensemble Everything Everywhere" Defense
2024/11/22 by Jie Zhang, Zhang, Jie, Christian Schlarmann +11 · 2 voices · 1 citation
#cs.LG #cs.CR
- Revisiting adapters with adversarial training
2022/10/10 by Sylvestre-Alvise Rebuffi, Rebuffi, Sylvestre-Alvise, Francesco Croce +3 · 1 citation
Computer Science · #Advanced Neural Network Applications #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Perturb and Recover: Fine-tuning for Effective Backdoor Removal from CLIP
2024/12/01 by Naman Deep Singh, Singh, Naman Deep, Francesco Croce +3 · 2 citations
Engineering · #Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Real-time simulation and control systems
- Adversarially Robust CLIP Models Can Induce Better (Robust) Perceptual Metrics
2025/02/17 by Francesco Croce, Christian Schlarmann, Croce, Francesco +5 · 2 citations
Computer Science · #Adversarial Robustness in Machine Learning