Luca Daniel

22 papers · 2018–2025 · 7 conferences · across top CS/AI conferences

Achievements

+13 more ↓

🐣 Hot Topic Early Bird 🌍 Conference Polyglot (7) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🏃 Academic Marathon (7)

🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🤝 Dynamic Duo (13) 👑 Triple Crown 🏆 Grand Slam 🏆 Keyword Champion (3) 🔥 Unstoppable (8) 🚀 Conference Pioneer ⚡ Prolific Year (6) ❓ The Questioner 🗃️ Keyword Collector (78) 💎 Century Club (22)

Conferences

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

Top co-authors

Pin-Yu Chen (13) Tsui-Wei Weng (8) Sijia Liu (8) Lily Weng (7) Ching-Yun Ko (7) Jeet Mohapatra (5) Akhilan Boopathy (4) Alexandre Megretski (3) Wang Zhang (3) Cho-jui Hsieh (3)

Keywords

adversarial robustness (11) neural network verification (5) neural network (5) adversarial attack (4) neural network robustness (3) adversarial perturbation (3) neural network certification (3) formal verification (2) randomized smoothing (2) contrastive learning (2) robustness certificate (2) adversarial defense (2) linear programming (2) certified robustness (2) robust reinforcement learning (1) robust optimization (1) policy learning (1) robust classification (1) adversarial learning (1) model quantization (1)

Papers

Large Language Models can Become Strong Self-Detoxifiers ICLR 2025 One Step Closer to Unbiased Aleatoric Uncertainty Estimation AAAI 2024 What Would Gauss Say About Representations? Probing Pretrained Image Models using Synthetic Gaussian Benchmarks ICML 2024 ConCerNet: A Contrastive Learning Based Framework for Automated Conservation Law Discovery and Trustworthy Dynamical System Prediction ICML 2023 Revisiting Contrastive Learning through the Lens of Neighborhood Component Analysis: an Integrated Framework ICML 2022 Adversarially Robust Conformal Prediction ICLR 2022 Learning from Multiple Annotator Noisy Labels via Sample-Wise Label Fusion ECCV 2022 Robust Deep Reinforcement Learning through Adversarial Loss NIPS 2021 Hidden Cost of Randomized Smoothing AISTATS 2021 Fast Training of Provably Robust Neural Networks by SingleProp AAAI 2021 Neural Network Control Policy Verification With Persistent Adversarial Perturbation ICML 2020 Fastened CROWN: Tightened Neural Network Robustness Certificates AAAI 2020 Towards Certificated Model Robustness Against Weight Perturbations AAAI 2020 Towards Verifying Robustness of Neural Networks Against A Family of Semantic Perturbations CVPR 2020 Higher-Order Certification For Randomized Smoothing NIPS 2020 Proper Network Interpretability Helps Adversarial Robustness in Classification ICML 2020 PROVEN: Verifying Robustness of Neural Networks with a Probabilistic Approach ICML 2019 CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks AAAI 2019 POPQORN: Quantifying Robustness of Recurrent Neural Networks ICML 2019 Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach ICLR 2018 Efficient Neural Network Robustness Certification with General Activation Functions NIPS 2018 Towards Fast Computation of Certified Robustness for ReLU Networks ICML 2018