IEEE SaTML 2023 Conference Submissions

Rethinking the Entropy of Instance in Adversarial Training
Minseon Kim, Jihoon Tack, Jinwoo Shin, Sung Ju Hwang
- 25 Aug 2022 (modified: 05 May 2023)
- SaTML 2023
- Readers: Everyone
Counterfactual Sentence Generation with Plug-and-Play Perturbation
Nishtha Madaan, Diptikalyan Saha, Srikanta J. Bedathur
- 24 Aug 2022 (modified: 05 May 2023)
- SaTML 2023
- Readers: Everyone
Distribution inference risks: Identifying and mitigating sources of leakage
Valentin Hartmann, Léo Meynent, Maxime Peyrard, Dimitrios Dimitriadis, Shruti Tople, Robert West
- 24 Aug 2022 (modified: 05 May 2023)
- SaTML 2023
- Readers: Everyone
SoK: Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks
Stephen Casper, Tilman Rauker, Anson Ho, Dylan Hadfield-Menell
- 24 Aug 2022 (modified: 05 May 2023)
- SaTML 2023
- Readers: Everyone
ModelPred: A Framework for Predicting Trained Model from Training Data
Yingyan Zeng, Tianhao Wang, Si Chen, Hoang Anh Just, Ran Jin, Ruoxi Jia
- 24 Aug 2022 (modified: 05 May 2023)
- SaTML 2023
- Readers: Everyone
Model Inversion Attack with Least Information and an In-depth Analysis of its Disparate Vulnerability
Sayanton V. Dibbo, Dae Lim Chung, Shagufta Mehnaz
- 24 Aug 2022 (modified: 05 May 2023)
- SaTML 2023
- Readers: Everyone
SoK: A Validity Perspective on Evaluating the Justified Use of Data-driven Decision-making Algorithms
Amanda Lee Coston, Anna Kawakami, Haiyi Zhu, Ken Holstein, Hoda Heidari
- 24 Aug 2022 (modified: 05 May 2023)
- SaTML 2023
- Readers: Everyone
FaShapley: Fast and Approximated Shapley Based Model Pruning Towards Certifiably Robust DNNs
Mintong Kang, Linyi Li, Bo Li
- 24 Aug 2022 (modified: 05 May 2023)
- SaTML 2023
- Readers: Everyone
VENOMAVE: Targeted Poisoning Against Speech Recognition
Hojjat Aghakhani, Lea Schönherr, Thorsten Eisenhofer, Dorothea Kolossa, Thorsten Holz, Christopher Kruegel, Giovanni Vigna
- 24 Aug 2022 (modified: 05 May 2023)
- SaTML 2023
- Readers: Everyone
What Are Effective Labels for Augmented Data? Improving Calibration and Robustness with AutoLabel
Yao Qin, Xuezhi Wang, Balaji Lakshminarayanan, Ed H. Chi, Alex Beutel
- 24 Aug 2022 (modified: 05 May 2023)
- SaTML 2023
- Readers: Everyone
Toward Certified Robustness Against Real-World Distribution Shifts
Haoze Wu, Teruhiro Tagomori, Alexander Robey, Fengjun Yang, Nikolai Matni, Hamed Hassani, George J. Pappas, Corina Pasareanu, Clark Barrett
- 24 Aug 2022 (modified: 22 Oct 2023)
- SaTML 2023
- Readers: Everyone
Position: Tensions Between the Proxies of Human Values in AI
Teresa Datta, Daniel Nissani, Max Cembalest, Akash Khanna, Haley Massa, John P Dickerson
- 24 Aug 2022 (modified: 05 May 2023)
- SaTML 2023
- Readers: Everyone
CARE: Certifiably Robust Learning with Reasoning via Variational Inference
Jiawei Zhang, Linyi Li, Ce Zhang, Bo Li
- 24 Aug 2022 (modified: 05 May 2023)
- SaTML 2023
- Readers: Everyone
Learning Fair Representations through Uniformly Distributed Sensitive Attributes
Patrik Joslin Kenfack, Adín Ramírez Rivera, Adil Khan, Manuel Mazzara
- 24 Aug 2022 (modified: 05 May 2023)
- SaTML 2023
- Readers: Everyone
Less is More: Dimension Reduction Finds On-Manifold Adversarial Examples in Hard-Label Attacks
Washington Garcia, Pin-Yu Chen, Hamilton Scott Clouse, Somesh Jha, Kevin R. B. Butler
- 24 Aug 2022 (modified: 05 May 2023)
- SaTML 2023
- Readers: Everyone
Position: “Real Attackers Don’t Compute Gradients”: Bridging the Gap Between Adversarial ML Research and Practice
Giovanni Apruzzese, Hyrum S Anderson, Savino Dambra, David Freeman, Fabio Pierazzi, Kevin Alejandro Roundy
- 24 Aug 2022 (modified: 05 May 2023)
- SaTML 2023
- Readers: Everyone
NEURAL LOWER BOUNDS FOR VERIFICATION
Florian Jaeckle, M. Pawan Kumar
- 24 Aug 2022 (modified: 05 May 2023)
- SaTML 2023
- Readers: Everyone
EDoG: Adversarial Edge Detection For Graph Neural Networks
Xiaojun Xu, Hanzhang Wang, Alok Lal, Carl A. Gunter, Bo Li
- 24 Aug 2022 (modified: 22 Oct 2023)
- SaTML 2023
- Readers: Everyone
Wealth Dynamics Over Generations: Analysis and Interventions
Krishna Acharya, Eshwar Ram Arunachaleswaran, Sampath Kannan, Aaron Roth, Juba Ziani
- 24 Aug 2022 (modified: 05 May 2023)
- SaTML 2023
- Readers: Everyone
Publishing Efficient On-device Models Increases Adversarial Vulnerability
Sanghyun Hong, Nicholas Carlini, Alexey Kurakin
- 24 Aug 2022 (modified: 05 May 2023)
- SaTML 2023
- Readers: Everyone
Kernel Normalized Convolutional Networks for Privacy-Preserving Machine Learning
Reza Nasirigerdeh, Javad Torkzadehmahani, Daniel Rueckert, Georgios Kaissis
- 24 Aug 2022 (modified: 05 May 2023)
- SaTML 2023
- Readers: Everyone
Backdoor Attacks on Time Series: A Generative Approach
Yujing Jiang, Xingjun Ma, Sarah Monazam Erfani, James Bailey
- 24 Aug 2022 (modified: 22 Oct 2023)
- SaTML 2023
- Readers: Everyone
Sniper Backdoor: Single Client Targeted Backdoor Attack in Federated Learning
Gorka Abad, Servio Paguada, Oguzhan Ersoy, Stjepan Picek, Victor Julio Ramírez-Durán, Aitor Urbieta
- 24 Aug 2022 (modified: 05 May 2023)
- SaTML 2023
- Readers: Everyone
Data Redaction from Pre-trained GANs
Zhifeng Kong, Kamalika Chaudhuri
- 24 Aug 2022 (modified: 05 May 2023)
- SaTML 2023
- Readers: Everyone
Reprogrammable-FL: Improving Utility-Privacy Tradeoff in Federated Learning via Model Reprogramming
Huzaifa Arif, Alex Gittens, Pin-Yu Chen
- 24 Aug 2022 (modified: 05 May 2023)
- SaTML 2023
- Readers: Everyone