default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDSaTML 2025: Copenhagen, Denmark
- IEEE Conference on Secure and Trustworthy Machine Learning, SaTML 2025, Copenhagen, Denmark, April 9-11, 2025. IEEE 2025, ISBN 979-8-3315-1711-3
- Ghaith Hammouri, Kemal Derya, Berk Sunar:
Non-Halting Queries: Exploiting Fixed Points in LLMs. 1-22 - Patrick Chao, Alexander Robey, Edgar Dobriban, Hamed Hassani, George J. Pappas, Eric Wong:
Jailbreaking Black Box Large Language Models in Twenty Queries. 23-42 - Sahar Abdelnabi, Aideen Fay, Giovanni Cherubin, Ahmed Salem, Mario Fritz, Andrew Paverd:
Get My Drift? Catching LLM Task Drift with Activation Deltas. 43-67 - Julien Piet, Chawin Sitawarin, Vivian Fang, Norman Mu, David A. Wagner:
MARKMyWORDS: Analyzing and Evaluating Language Model Watermarks. 68-91 - Mahmoud Ghorbel, Halima Bouzidi, Ioan Marius Bilasco, Ihsen Alouani:
SnatchML: Hijacking ML Models Without Training Access. 92-109 - Caspar Meijer, Jiyue Huang, Shreshtha Sharma, Elena Lazovik, Lydia Y. Chen:
TS-Inverse: A Gradient Inversion Attack Tailored for Federated Time Series Forecasting Models. 110-124 - Huzaifa Arif, Keerthiram Murugesan, Payel Das, Alex Gittens, Pin-Yu Chen:
PEEL the Layers and Find Yourself: Revisiting Inference-Time Data Leakage for Residual Neural Networks. 125-149 - Daryna Oliynyk, Rudolf Mayer, Andreas Rauber:
Attackers Can Do Better: Over- and Understated Factors of Model Stealing Attacks. 150-168 - Hengrui Jia, Sierra Calanda Wyllie, Akram Bin Sediq, Ahmed Ibrahim, Nicolas Papernot:
Backdoor Detection Through Replicated Execution of Outsourced Training. 169-188 - Ebtisaam Alharbi, Leandro Soriano Marcolino, Qiang Ni, Antonios Gouglidis:
Robust Knowledge Distillation in Federated Learning: Counteracting Backdoor Attacks. 189-202 - Ying Song, Rita Singh, Balaji Palanisamy:
Krait: A Backdoor Attack Against Graph Prompt Tuning. 203-221 - Wencong You, Daniel Lowd:
The Ultimate Cookbook for Invisible Poison: Crafting Subtle Clean-Label Text Backdoors with Style Attributes. 222-246 - Saskia Laura Schröer, Giovanni Apruzzese, Soheil Human, Pavel Laskov, Hyrum S. Anderson, Edward W. N. Bernroider, Aurore Fass, Ben Nassi, Vera Rimmer, Fabio Roli, Samer Salam, Chi En Ashley Shen, Ali Sunyaev, Tim Wadhwa-Brown, Isabel Wagner, Gang Wang:
SoK: On the Offensive Potential of AI. 247-280 - Shrey Jain, Zoë Hitzig, Pamela Mishkin:
Position: Contextual Confidence and Generative AI. 281-301 - Eleanor Clifford, Adhithya Saravanan, Harry Langford, Cheng Zhang, Yiren Zhao, Robert D. Mullins, Ilia Shumailov, Jamie Hayes:
Locking Machine Learning Models into Hardware. 302-320 - Chad DeChant:
Episodic Memory in AI Agents Poses Risks that Should be Studied and Mitigated. 321-332 - Jie Zhang, Debeshee Das, Gautam Kamath, Florian Tramèr:
Position: Membership Inference Attacks Cannot Prove That a Model was Trained on Your Data. 333-345 - Jiashu Tao, Reza Shokri:
Range Membership Inference Attacks. 346-361 - Gauri Pradhan, Joonas Jälkö, Marlon Tobaben, Antti Honkela:
Hyperparameters in Score-Based Membership Inference Attacks. 362-384 - Matthieu Meeus, Igor Shilov, Shubham Jain, Manuel Faysse, Marek Rei, Yves-Alexandre de Montjoye:
SoK: Membership Inference Attacks on LLMs are Rushing Nowhere (and How to Fix It). 385-401 - Hugo Lyons Keenan, Sarah M. Erfani, Christopher Leckie:
HALO: Robust Out-of-Distribution Detection via Joint Optimisation. 402-426 - Banibrata Ghosh, Haripriya Harikumar, Svetha Venkatesh, Santu Rana:
Targeted Manifold Manipulation Against Adversarial Attacks. 427-438 - Yue Gao, Ilia Shumailov, Kassem Fawaz:
SEA: Shareable and Explainable Attribution for Query-Based Black-Box Attacks. 439-458 - Mauricio Byrd Victorica, György Dán, Henrik Sandberg:
SpaNN: Detecting Multiple Adversarial Patches on CNNs by Spanning Saliency Thresholds. 459-478 - Thorsten Eisenhofer, Doreen Riepel, Varun Chandrasekaran, Esha Ghosh, Olga Ohrimenko, Nicolas Papernot:
Verifiable and Provably Secure Machine Unlearning. 479-496 - Jamie Hayes, Ilia Shumailov, Eleni Triantafillou, Amr Khalifa, Nicolas Papernot:
Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy. 497-519 - Pratiksha Thaker, Shengyuan Hu, Neil Kale, Yash Maurya, Zhiwei Steven Wu, Virginia Smith:
Position: LLM Unlearning Benchmarks are Weak Measures of Progress. 520-533 - Amrita Roy Chowdhury, Zhifeng Kong, Kamalika Chaudhuri:
On the Reliability of Membership Inference Attacks. 534-549 - Diptangshu Sen, Jingyan Wang, Juba Ziani:
Equilibria of Data Marketplaces with Privacy-Aware Sellers under Endogenous Privacy Costs. 550-574 - Joel Daniel Andersson, Rasmus Pagh:
Streaming Private Continual Counting via Binning. 575-589 - Sajani Vithana, Viveck R. Cadambe, Flávio P. Calmon, Haewon Jeong:
Correlated Privacy Mechanisms for Differentially Private Distributed Mean Estimation. 590-614 - Daniela Antonova, Allegra Laro, Audra McMillan, Lorenz Wolf:
Private Selection with Heterogeneous Sensitivities. 615-635 - Francesco Croce, Christian Schlarmann, Naman Deep Singh, Matthias Hein:
Adversarially Robust CLIP Models Can Induce Better (Robust) Perceptual Metrics. 636-660 - Blaine Hoak, Ryan Sheatsley, Patrick D. McDaniel:
Err on the Side of Texture: Texture Bias on Real Data. 661-680 - Ming-Chang Chiu, Yingfei Wang, Derrick Eui Gyu Kim, Pin-Yu Chen, Xuezhe Ma:
ColorSense: A Study on Color Vision in Machine Visual Recognition. 681-697 - John Dickerson, Seyed A. Esmaeili, Jamie Morgenstern, Claire Jie Zhang:
SoK: Fair Clustering: Critique, Caveats, and Future Directions. 698-713 - Sayan Biswas, Anne-Marie Kermarrec, Rishi Sharma, Trinca Thibaud, Martijn de Vos:
Fair Decentralized Learning. 714-734 - Natasa Krco, Thibault Laugel, Vincent Grari, Jean-Michel Loubes, Marcin Detyniecki:
When Mitigating Bias is Unfair: Multiplicity and Arbitrariness in Algorithmic Group Fairness. 735-752 - Emily Diana, Saeed Sharifi-Malvajerdi, Ali Vakilian:
Minimax Group Fairness in Strategic Classification. 753-772 - Yunjuan Wang, Hussein Hazimeh, Natalia Ponomareva, Alexey Kurakin, Ibrahim Hammoud, Raman Arora:
DART: A Principled Approach to Adversarially Robust Unsupervised Domain Adaptation. 773-796 - Wenqian Yu, Jindong Gu, Zhijiang Li, Philip Torr:
Reliable Evaluation of Adversarial Transferability. 797-810 - Alexandra Arzberger
, Ramin Tavakoli Kolagari:
Hi-ALPS - An Experimental Robustness Quantification of Six LiDAR-based Object Detection Systems for Autonomous Driving. 811-823 - Stefano Calzavara, Lorenzo Cazzaro, Massimo Vettori:
Timber! Poisoning Decision Trees. 824-840 - Kai Yao, Marc Juarez:
SoK: What Makes Private Learning Unfair? 841-857 - Kristian Schwethelm, Johannes Kaiser, Jonas Kuntzer, Mehmet Yigitsoy, Daniel Rückert, Georgios Kaissis:
Differentially Private Active Learning: Balancing Effective Data Selection and Privacy. 858-878 - Xin Gu, Gautam Kamath, Zhiwei Steven Wu:
Choosing Public Datasets for Private Machine Learning via Gradient Subspace Distance. 879-900 - Zachary Charles, Arun Ganesh, Ryan McKenna, H. Brendan McMahan, Nicole Mitchell, Krishna Pillutla, Keith Rush:
Learning with User-Level Differential Privacy Under Fixed Compute Budgets. 901-920 - Yigitcan Kaya, Yizheng Chen, Marcus Botacin, Shoumik Saha, Fabio Pierazzi, Lorenzo Cavallaro, David A. Wagner, Tudor Dumitras:
ML-Based Behavioral Malware Detection Is Far From a Solved Problem. 921-940 - Luke A. Bauer, Wenxuan Bao, Vincent Bindschaedler:
Provably Secure Covert Messaging Using Image-Based Diffusion Processes. 941-955 - Khang Tran, Ferdinando Fioretto, Issa Khalil, My T. Thai, Linh Thi Xuan Phan, NhatHai Phan:
FairDP: Achieving Fairness Certification with Differential Privacy. 956-976 - Steven Golob, Sikha Pentyala, Anuar Maratkhan, Martine De Cock:
Privacy Vulnerabilities in Marginals-based Synthetic Data. 977-995 - Christian Janos Lebeda, Matthew Regehr, Gautam Kamath, Thomas Steinke:
Avoiding Pitfalls for Privacy Accounting of Subsampled Mechanisms Under Composition. 996-1006 - Antti Koskela, Jafar Mohammadi:
Auditing Differential Privacy Guarantees Using Density Estimation. 1007-1026
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
last updated on 2025-06-24 21:41 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
