1. Home
  2. Proceedings
  3. SATML
  4. SATML 2024
Default Cover Image

2024 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)

April 9 2024 to April 11 2024

Toronto, ON, Canada

ISBN: 979-8-3503-4950-4

Table of Contents

Title Page iFreely available from IEEE.pp. 1-1
Title Page iiiFreely available from IEEE.pp. 3-3
Copyright PageFreely available from IEEE.pp. 4-4
Table of ContentsFreely available from IEEE.pp. 5-9
Message from the Program ChairsFreely available from IEEE.pp. 10-10
Organizing CommitteeFreely available from IEEE.pp. 11-11
Program CommitteeFreely available from IEEE.pp. 12-14
Steering CommitteeFreely available from IEEE.pp. 15-15
Probabilistic Dataset Reconstruction from Interpretable ModelsFull-text access may be available. Sign in or learn about subscription options.pp. 1-17
by Julien Ferry, Ulrich Aïvodji, Sébastien Gambs, Marie-José Huguet, Mohamed Siala
Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy RiskFull-text access may be available. Sign in or learn about subscription options.pp. 18-32
by Zhangheng Li, Junyuan Hong, Bo Li, Zhangyang Wang
Improved Differentially Private Regression via Gradient BoostingFull-text access may be available. Sign in or learn about subscription options.pp. 33-56
by Shuai Tang, Sergul Aydore, Michael Kearns, Saeyoung Rho, Aaron Roth, Yichen Wang, Yu-Xiang Wang, Zhiwei Steven Wu
SoK: A Review of Differentially Private Linear Models For High-Dimensional DataFull-text access may be available. Sign in or learn about subscription options.pp. 57-77
by Amol Khanna, Edward Raff, Nathan Inkawhich
Concentrated Differential Privacy for BanditsFull-text access may be available. Sign in or learn about subscription options.pp. 78-109
by Achraf Azize, Debabrota Basu
PILLAR: How to make semi-private learning more effectiveFull-text access may be available. Sign in or learn about subscription options.pp. 110-139
by Francesco Pinto, Yaxi Hu, Fanny Yang, Amartya Sanyal
Fair Federated Learning via Bounded Group LossFull-text access may be available. Sign in or learn about subscription options.pp. 140-160
by Shengyuan Hu, Zhiwei Steven Wu, Virginia Smith
Estimating and Implementing Conventional Fairness Metrics With Probabilistic Protected FeaturesFull-text access may be available. Sign in or learn about subscription options.pp. 161-193
by Hadi Elzayn, Emily Black, Patrick Vossler, Nathanael Jo, Jacob Goldin, Daniel E. Ho
Evaluating Superhuman Models with Consistency ChecksFull-text access may be available. Sign in or learn about subscription options.pp. 194-232
by Lukas Fluri, Daniel Paleka, Florian Tramèr
Certifiably Robust Reinforcement Learning through Model-Based Abstract InterpretationFull-text access may be available. Sign in or learn about subscription options.pp. 233-251
by Chenxi Yang, Greg Anderson, Swarat Chaudhuri
Fast Certification of Vision-Language Models Using Incremental Randomized SmoothingFull-text access may be available. Sign in or learn about subscription options.pp. 252-271
by Ashutosh Nirala, Ameya Joshi, Soumik Sarkar, Chinmay Hegde
Backdoor Attack on Unpaired Medical Image-Text Foundation Models: A Pilot Study on MedCLIPFull-text access may be available. Sign in or learn about subscription options.pp. 272-285
by Ruinan Jin, Chun-Yin Huang, Chenyu You, Xiaoxiao Li
REStore: Exploring a Black-Box Defense against DNN Backdoors using Rare Event SimulationFull-text access may be available. Sign in or learn about subscription options.pp. 286-308
by Quentin Le Roux, Kassem Kallas, Teddy Furon
EdgePruner: Poisoned Edge Pruning in Graph Contrastive LearningFull-text access may be available. Sign in or learn about subscription options.pp. 309-326
by Hiroya Kato, Kento Hasegawa, Seira Hidano, Kazuhide Fukushima
Indiscriminate Data Poisoning Attacks on Pre-trained Feature ExtractorsFull-text access may be available. Sign in or learn about subscription options.pp. 327-343
by Yiwei Lu, Matthew Y. R. Yang, Gautam Kamath, Yaoliang Yu
ImpNet: Imperceptible and blackbox-undetectable backdoors in compiled neural networksFull-text access may be available. Sign in or learn about subscription options.pp. 344-357
by Eleanor Clifford, Ilia Shumailov, Yiren Zhao, Ross Anderson, Robert Mullins
The Devil’s Advocate: Shattering the Illusion of Unexploitable Data using Diffusion ModelsFull-text access may be available. Sign in or learn about subscription options.pp. 358-386
by Hadi M. Dolatabadi, Sarah Erfani, Christopher Leckie
SoK: Pitfalls in Evaluating Black-Box AttacksFull-text access may be available. Sign in or learn about subscription options.pp. 387-407
by Fnu Suya, Anshuman Suri, Tingwei Zhang, Jingtao Hong, Yuan Tian, David Evans
Evading Black-box Classifiers Without Breaking EggsFull-text access may be available. Sign in or learn about subscription options.pp. 408-424
by Edoardo Debenedetti, Nicholas Carlini, Florian Tramèr
Segment (Almost) Nothing: Prompt-Agnostic Adversarial Attacks on Segmentation ModelsFull-text access may be available. Sign in or learn about subscription options.pp. 425-442
by Francesco Croce, Matthias Hein
Improving Privacy-Preserving Vertical Federated Learning by Efficient Communication with ADMMFull-text access may be available. Sign in or learn about subscription options.pp. 443-471
by Chulin Xie, Pin-Yu Chen, Qinbin Li, Arash Nourian, Ce Zhang, Bo Li
Differentially Private Multi-Site Treatment Effect EstimationFull-text access may be available. Sign in or learn about subscription options.pp. 472-489
by Tatsuki Koga, Kamalika Chaudhuri, David Page
ScionFL: Efficient and Robust Secure Quantized AggregationFull-text access may be available. Sign in or learn about subscription options.pp. 490-511
by Yaniv Ben-Itzhak, Helen Möllering, Benny Pinkas, Thomas Schneider, Ajith Suresh, Oleksandr Tkachenko, Shay Vargaftik, Christian Weinert, Hossein Yalame, Avishay Yanai
Differentially Private Heavy Hitter Detection using Federated AnalyticsFull-text access may be available. Sign in or learn about subscription options.pp. 512-533
by Karan Chadha, Junye Chen, John Duchi, Vitaly Feldman, Hanieh Hashemi, Omid Javidbakht, Audra McMillan, Kunal Talwar
Olympia: A Simulation Framework for Evaluating the Concrete Scalability of Secure Aggregation ProtocolsFull-text access may be available. Sign in or learn about subscription options.pp. 534-551
by Ivoline C. Ngong, Nicholas Gibson, Joseph P. Near
Model Reprogramming Outperforms Fine-tuning on Out-of-distribution Data in Text-Image EncodersFull-text access may be available. Sign in or learn about subscription options.pp. 552-568
by Andrew Geng, Pin-Yu Chen
Data Redaction from Conditional Generative ModelsFull-text access may be available. Sign in or learn about subscription options.pp. 569-591
by Zhifeng Kong, Kamalika Chaudhuri
Towards Scalable and Robust Model VersioningFull-text access may be available. Sign in or learn about subscription options.pp. 592-611
by Wenxin Ding, Arjun Nitin Bhagoji, Ben Y. Zhao, Haitao Zheng
AI auditing: The Broken Bus on the Road to AI AccountabilityFull-text access may be available. Sign in or learn about subscription options.pp. 612-643
by Abeba Birhane, Ryan Steed, Victor Ojewale, Briana Vecchione, Inioluwa Deborah Raji
Under manipulations, are some AI models harder to audit?Full-text access may be available. Sign in or learn about subscription options.pp. 644-664
by Augustin Godinot, Erwan Le Merrer, Gilles Trédan, Camilla Penzo, Franois Taïani
Unifying Corroborative and Contributive Attributions in Large Language ModelsFull-text access may be available. Sign in or learn about subscription options.pp. 665-683
by Theodora Worledge, Judy Hanwen Shen, Nicole Meister, Caleb Winston, Carlos Guestrin
CodeLMSec Benchmark: Systematically Evaluating and Finding Security Vulnerabilities in Black-Box Code Language ModelsFull-text access may be available. Sign in or learn about subscription options.pp. 684-709
by Hossein Hajipour, Keno Hassler, Thorsten Holz, Lea Schönherr, Mario Fritz
Navigating the Structured What-If Spaces: Counterfactual Generation via Structured DiffusionFull-text access may be available. Sign in or learn about subscription options.pp. 710-722
by Nishtha Madaan, Srikanta Bedathur
Understanding, Uncovering, and Mitigating the Causes of Inference Slowdown for Language ModelsFull-text access may be available. Sign in or learn about subscription options.pp. 723-740
by Kamala Varma, Arda Numanoğlu, Yigitcan Kaya, Tudor Dumitraş
Author IndexFreely available from IEEE.pp. 741-742
Showing 43 out of 43