ICML 2023 Workshop AdvML-Frontiers Submissions

Benchmarking the Reliability of Post-training Quantization: a Particular Focus on Worst-case Performance
Zhihang Yuan, Jiawei Liu, Jiaxiang Wu, Dawei Yang, Qiang Wu, Guangyu Sun, Wenyu Liu, Xinggang Wang, Bingzhe Wu
- Published: 20 Jun 2023, Last Modified: 07 Aug 2023
- AdvML-Frontiers 2023
- Readers: Everyone
Benchmarking Adversarial Robustness of Compressed Deep Learning Models
Brijesh Vora, Kartik Patwari, Syed Mahbub Hafiz, Zubair Shafiq, Chen-Nee Chuah
- Published: 20 Jun 2023, Last Modified: 07 Aug 2023
- AdvML-Frontiers 2023
- Readers: Everyone
Robustness through Data Augmentation Loss Consistency
Tianjian Huang, Shaunak Halbe, Chinnadhurai Sankar, Pooyan Amini, Satwik Kottur, Alborz Geramifard, Meisam Razaviyayn, Ahmad Beirami
- Published: 20 Jun 2023, Last Modified: 07 Aug 2023
- AdvML-Frontiers 2023
- Readers: Everyone
Expressivity of Graph Neural Networks Through the Lens of Adversarial Robustness
Francesco Campi, Lukas Gosch, Tom Wollschläger, Yan Scholten, Stephan Günnemann
- Published: 20 Jun 2023, Last Modified: 07 Aug 2023
- AdvML-Frontiers 2023
- Readers: Everyone
Visual Adversarial Examples Jailbreak Aligned Large Language Models
Xiangyu Qi, Kaixuan Huang, Ashwinee Panda, Mengdi Wang, Prateek Mittal
- Published: 20 Jun 2023, Last Modified: 07 Aug 2023
- AdvML-Frontiers 2023
- Readers: Everyone
The Future of Cyber Systems: Human-AI Reinforcement Learning with Adversarial Robustness
Nicole Nichols
- Published: 20 Jun 2023, Last Modified: 07 Aug 2023
- AdvML-Frontiers 2023
- Readers: Everyone
Provably Robust Cost-Sensitive Learning via Randomized Smoothing
Yuan Xin, Michael Backes, Xiao Zhang
- Published: 20 Jun 2023, Last Modified: 07 Aug 2023
- AdvML-Frontiers 2023
- Readers: Everyone
Like Oil and Water: Group Robustness and Poisoning Defenses Don’t Mix
Michael-Andrei Panaitescu-Liess, Yigitcan Kaya, Tudor Dumitras
- Published: 20 Jun 2023, Last Modified: 07 Aug 2023
- AdvML-Frontiers 2023
- Readers: Everyone
Provable Instance Specific Robustness via Linear Constraints
Ahmed Imtiaz Humayun, Josue Casco-Rodriguez, Randall Balestriero, Richard Baraniuk
- Published: 20 Jun 2023, Last Modified: 07 Aug 2023
- AdvML-Frontiers 2023
- Readers: Everyone
Adversarial Training in Continuous-Time Models and Irregularly Sampled Time-Series
Alvin Li, Mathias Lechner, Alexander Amini, Daniela Rus
- Published: 20 Jun 2023, Last Modified: 07 Aug 2023
- AdvML-Frontiers 2023
- Readers: Everyone
Few-shot Anomaly Detection via Personalization
Sangkyung Kwak, Jongheon Jeong, Hankook Lee, Woohyuck Kim, Jinwoo Shin
- Published: 20 Jun 2023, Last Modified: 07 Aug 2023
- AdvML-Frontiers 2023
- Readers: Everyone
Rethinking Label Poisoning for GNNs: Pitfalls and Attacks
Vijay Lingam, Mohammad Sadegh Akhondzadeh, Aleksandar Bojchevski
- Published: 20 Jun 2023, Last Modified: 07 Aug 2023
- AdvML-Frontiers 2023
- Readers: Everyone
Shrink & Cert: Bi-level Optimization for Certified Robustness
Kavya Gupta, Sagar Verma
- Published: 20 Jun 2023, Last Modified: 07 Aug 2023
- AdvML-Frontiers 2023
- Readers: Everyone
Preventing Reward Hacking with Occupancy Measure Regularization
Cassidy Laidlaw, Shivam Singhal, Anca Dragan
- Published: 20 Jun 2023, Last Modified: 07 Aug 2023
- AdvML-Frontiers 2023
- Readers: Everyone
Evading Black-box Classifiers Without Breaking Eggs
Edoardo Debenedetti, Nicholas Carlini, Florian Tramèr
- Published: 20 Jun 2023, Last Modified: 07 Aug 2023
- AdvML-Frontiers 2023
- Readers: Everyone
Deceptive Alignment Monitoring
Andres Carranza, Dhruv Bhandarkar Pai, Rylan Schaeffer, Arnuv Tandon, Sanmi Koyejo
- Published: 20 Jun 2023, Last Modified: 07 Aug 2023
- AdvML-Frontiers 2023
- Readers: Everyone
Baselines for Identifying Watermarked Large Language Models
Leonard Tang, Gavin Uberti, Tom Shlomi
- Published: 20 Jun 2023, Last Modified: 07 Aug 2023
- AdvML-Frontiers 2023
- Readers: Everyone
Why do universal adversarial attacks work on large language models?: Geometry might be the answer
Varshini Subhash, Anna Bialas, Weiwei Pan, Finale Doshi-Velez
- Published: 20 Jun 2023, Last Modified: 07 Aug 2023
- AdvML-Frontiers 2023
- Readers: Everyone
FACADE: A Framework for Adversarial Circuit Anomaly Detection and Evaluation
Dhruv Bhandarkar Pai, Andres Carranza, Rylan Schaeffer, Arnuv Tandon, Sanmi Koyejo
- Published: 20 Jun 2023, Last Modified: 07 Aug 2023
- AdvML-Frontiers 2023
- Readers: Everyone
Robust Deep Learning via Layerwise Tilted Exponentials
Bhagyashree Puranik, Ahmad Beirami, Yao Qin, Upamanyu Madhow
- Published: 20 Jun 2023, Last Modified: 07 Aug 2023
- AdvML-Frontiers 2023
- Readers: Everyone
Learning Shared Safety Constraints from Multi-task Demonstrations
Konwoo Kim, Gokul Swamy, Zuxin Liu, Ding Zhao, Sanjiban Choudhury, Steven Wu
- Published: 20 Jun 2023, Last Modified: 07 Aug 2023
- AdvML-Frontiers 2023
- Readers: Everyone
Teach GPT To Phish
Ashwinee Panda, Zhengming Zhang, Yaoqing Yang, Prateek Mittal
- Published: 20 Jun 2023, Last Modified: 07 Aug 2023
- AdvML-Frontiers 2023
- Readers: Everyone
How Can Neuroscience Help Us Build More Robust Deep Neural Networks?
Sayanton V. Dibbo, Siddharth Mansingh, Jocelyn Rego, Garrett T. Kenyon, Juston Moore, Michael Teti
- Published: 20 Jun 2023, Last Modified: 07 Aug 2023
- AdvML-Frontiers 2023
- Readers: Everyone
Physics-oriented adversarial attacks on SAR image target recognition
Jiahao Cui, wang Guo, Run Shao, tiandong Shi, Haifeng Li
- Published: 20 Jun 2023, Last Modified: 07 Aug 2023
- AdvML-Frontiers 2023
- Readers: Everyone
Accurate, Explainable, and Private Models: Providing Recourse While Minimizing Training Data Leakage
Catherine Huang, Chelse Swoopes, Christina Xiao, Jiaqi Ma, Himabindu Lakkaraju
- Published: 20 Jun 2023, Last Modified: 07 Aug 2023
- AdvML-Frontiers 2023
- Readers: Everyone