SaTML

Publications

2024

Francesco Croce, Matthias Hein
Segment (Almost) Nothing: Prompt-Agnostic Adversarial Attacks on Segmentation Models. SaTML (2024)
Nishtha Madaan, Srikanta Bedathur
Navigating the Structured What-If Spaces: Counterfactual Generation via Structured Diffusion. SaTML (2024)
Fnu Suya, Anshuman Suri, Tingwei Zhang, Jingtao Hong, Yuan Tian, David Evans
SoK: Pitfalls in Evaluating Black-Box Attacks. SaTML (2024)
Quentin Le Roux, Kassem Kallas, Teddy Furon
REStore: Exploring a Black-Box Defense against DNN Backdoors using Rare Event Simulation. SaTML (2024)
Edoardo Debenedetti, Nicholas Carlini, Florian Tramèr
Evading Black-box Classifiers Without Breaking Eggs. SaTML (2024)
Andrew Geng, Pin-Yu Chen
Model Reprogramming Outperforms Fine-tuning on Out-of-distribution Data in Text-Image Encoders. SaTML (2024)
Hadi Elzayn, Emily Black, Patrick Vossler, Nathanael Jo, Jacob Goldin, Daniel E. Ho
Estimating and Implementing Conventional Fairness Metrics With Probabilistic Protected Features. SaTML (2024)
Ruinan Jin, Chun-Yin Huang, Chenyu You, Xiaoxiao Li
Backdoor Attack on Unpaired Medical Image-Text Foundation Models: A Pilot Study on MedCLIP. SaTML (2024)
Julien Ferry, Ulrich Aïvodji, Sébastien Gambs, Marie-José Huguet, Mohamed Siala
Probabilistic Dataset Reconstruction from Interpretable Models. SaTML (2024)
Chulin Xie, Pin-Yu Chen, Qinbin Li, Arash Nourian, Ce Zhang, Bo Li
Improving Privacy-Preserving Vertical Federated Learning by Efficient Communication with ADMM. SaTML (2024)
Kamala Varma, Arda Numanoglu, Yigitcan Kaya, Tudor Dumitras
Understanding, Uncovering, and Mitigating the Causes of Inference Slowdown for Language Models. SaTML (2024)
Hadi M. Dolatabadi, Sarah M. Erfani, Christopher Leckie
The Devil's Advocate: Shattering the Illusion of Unexploitable Data using Diffusion Models. SaTML (2024)
Tatsuki Koga, Kamalika Chaudhuri, David Page
Differentially Private Multi-Site Treatment Effect Estimation. SaTML (2024)
Chenxi Yang, Greg Anderson, Swarat Chaudhuri
Certifiably Robust Reinforcement Learning through Model-Based Abstract Interpretation. SaTML (2024)
Augustin Godinot, Erwan Le Merrer, Gilles Trédan, Camilla Penzo, François Taïani
Under manipulations, are some AI models harder to audit? SaTML (2024)
Karan N. Chadha, Junye Chen, John C. Duchi, Vitaly Feldman, Hanieh Hashemi, Omid Javidbakht, Audra McMillan, Kunal Talwar
Differentially Private Heavy Hitter Detection using Federated Analytics. SaTML (2024)
Ivoline C. Ngong, Nicholas Gibson, Joseph P. Near
Olympia: A Simulation Framework for Evaluating the Concrete Scalability of Secure Aggregation Protocols. SaTML (2024)
Eleanor Clifford, Ilia Shumailov, Yiren Zhao, Ross J. Anderson, Robert D. Mullins
ImpNet: Imperceptible and blackbox-undetectable backdoors in compiled neural networks. SaTML (2024)
Ashutosh Nirala, Ameya Joshi, Soumik Sarkar, Chinmay Hegde
Fast Certification of Vision-Language Models Using Incremental Randomized Smoothing. SaTML (2024)
Yaniv Ben-Itzhak, Helen Möllering, Benny Pinkas, Thomas Schneider, Ajith Suresh, Oleksandr Tkachenko, Shay Vargaftik, Christian Weinert, Hossein Yalame, Avishay Yanai
ScionFL: Efficient and Robust Secure Quantized Aggregation. SaTML (2024)
Shuai Tang, Sergül Aydöre, Michael Kearns, Saeyoung Rho, Aaron Roth, Yichen Wang, Yu-Xiang Wang, Zhiwei Steven Wu
Improved Differentially Private Regression via Gradient Boosting. SaTML (2024)
Zhifeng Kong, Kamalika Chaudhuri
Data Redaction from Conditional Generative Models. SaTML (2024)
Wenxin Ding, Arjun Nitin Bhagoji, Ben Y. Zhao, Haitao Zheng
Towards Scalable and Robust Model Versioning. SaTML (2024)
Achraf Azize, Debabrota Basu
Concentrated Differential Privacy for Bandits. SaTML (2024)
IEEE Conference on Secure and Trustworthy Machine Learning, SaTML 2024, Toronto, ON, Canada, April 9-11, 2024 SaTML (2024)
Theodora Worledge, Judy Hanwen Shen, Nicole Meister, Caleb Winston, Carlos Guestrin
Unifying Corroborative and Contributive Attributions in Large Language Models. SaTML (2024)
Amol Khanna, Edward Raff, Nathan Inkawhich
SoK: A Review of Differentially Private Linear Models For High-Dimensional Data. SaTML (2024)
Lukas Fluri, Daniel Paleka, Florian Tramèr
Evaluating Superhuman Models with Consistency Checks. SaTML (2024)
Hossein Hajipour, Keno Hassler, Thorsten Holz, Lea Schönherr, Mario Fritz
CodeLMSec Benchmark: Systematically Evaluating and Finding Security Vulnerabilities in Black-Box Code Language Models. SaTML (2024)
Shengyuan Hu, Zhiwei Steven Wu, Virginia Smith
Fair Federated Learning via Bounded Group Loss. SaTML (2024)
Zhangheng Li, Junyuan Hong, Bo Li, Zhangyang Wang
Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk. SaTML (2024)
Hiroya Kato, Kento Hasegawa, Seira Hidano, Kazuhide Fukushima
EdgePruner: Poisoned Edge Pruning in Graph Contrastive Learning. SaTML (2024)
Francesco Pinto, Yaxi Hu, Fanny Yang, Amartya Sanyal
PILLAR: How to make semi-private learning more effective. SaTML (2024)
Abeba Birhane, Ryan Steed, Victor Ojewale, Briana Vecchione, Inioluwa Deborah Raji
AI auditing: The Broken Bus on the Road to AI Accountability. SaTML (2024)
Yiwei Lu, Matthew Y. R. Yang, Gautam Kamath, Yaoliang Yu
Indiscriminate Data Poisoning Attacks on Pre-trained Feature Extractors. SaTML (2024)

2023