Follow
Yuxin Wen
Title
Cited by
Cited by
Year
A watermark for large language models
J Kirchenbauer, J Geiping, Y Wen, J Katz, I Miers, T Goldstein
International Conference on Machine Learning (ICML) 2023, 2023
5072023
Baseline defenses for adversarial attacks against aligned language models
N Jain, A Schwarzschild, Y Wen, G Somepalli, J Kirchenbauer, P Chiang, ...
arXiv preprint arXiv:2309.00614, 2023
194*2023
Hard prompts made easy: Gradient-based discrete optimization for prompt tuning and discovery
Y Wen, N Jain, J Kirchenbauer, M Goldblum, J Geiping, T Goldstein
Conference on Neural Information Processing Systems (NeurIPS) 2023, 2023
1652023
On the Reliability of Watermarks for Large Language Models
J Kirchenbauer, J Geiping, Y Wen, M Shu, K Saifullah, K Kong, ...
International Conference on Learning Representations (ICLR) 2024, 2024
124*2024
Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust
Y Wen, J Kirchenbauer, J Geiping, T Goldstein
Conference on Neural Information Processing Systems (NeurIPS) 2023, 2023
86*2023
Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification
Y Wen, J Geiping, L Fowl, M Goldblum, T Goldstein
International Conference on Machine Learning (ICML) 2022, 2022
812022
NEFTune: Noisy Embeddings Improve Instruction Finetuning
N Jain, P Chiang, Y Wen, J Kirchenbauer, HM Chu, G Somepalli, ...
International Conference on Learning Representations (ICLR) 2024, 2024
55*2024
Decepticons: Corrupted transformers breach privacy in federated learning for language models
L Fowl, J Geiping, S Reich, Y Wen, W Czaja, M Goldblum, T Goldstein
International Conference on Learning Representations (ICLR) 2023, 2022
482022
Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries
Y Wen, A Bansal, H Kazemi, E Borgnia, M Goldblum, J Geiping, ...
International Conference on Learning Representations (ICLR) 2023, 2022
262022
Detecting, Explaining, and Mitigating Memorization in Diffusion Models
Y Wen, Y Liu, C Chen, L Lyu
International Conference on Learning Representations (ICLR) 2024, 2024
212024
Bring your own data! self-supervised evaluation for large language models
N Jain, K Saifullah, Y Wen, J Kirchenbauer, M Shu, A Saha, M Goldblum, ...
Conference on Language Modeling (COLM) 2024, 2023
202023
Coercing LLMs to do and reveal (almost) anything
J Geiping, A Stein, M Shu, K Saifullah, Y Wen, T Goldstein
arXiv preprint arXiv:2402.14020, 2024
192024
Benchmarking the Robustness of Image Watermarks
B An, M Ding, T Rabbani, A Agrawal, Y Xu, C Deng, S Zhu, A Mohamed, ...
International Conference on Machine Learning (ICML) 2024, 2024
132024
Thinking Two Moves Ahead: Anticipating Other Users Improves Backdoor Attacks in Federated Learning
Y Wen, J Geiping, L Fowl, H Souri, R Chellappa, M Goldblum, T Goldstein
AdvML Frontiers Workshop, ICML 2022, 2022
102022
Privacy backdoors: Enhancing membership inference through poisoning pre-trained models
Y Wen, L Marchyok, S Hong, J Geiping, T Goldstein, N Carlini
Conference on Neural Information Processing Systems (NeurIPS) 2024, 2024
62024
Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs
A Hans, Y Wen, N Jain, J Kirchenbauer, H Kazemi, P Singhania, S Singh, ...
Conference on Neural Information Processing Systems (NeurIPS) 2024, 2024
3*2024
Is Synthetic Image Useful for Transfer Learning? An Investigation into Data Generation, Volume, and Utilization
Y Li, X Dong, C Chen, J Li, Y Wen, M Spranger, L Lyu
arXiv preprint arXiv:2403.19866, 2024
32024
GenQA: Generating Millions of Instructions from a Handful of Prompts
J Chen, R Qadri, Y Wen, N Jain, J Kirchenbauer, T Zhou, T Goldstein
arXiv preprint arXiv:2406.10323, 2024
22024
Styx: Adaptive Poisoning Attacks against Byzantine-Robust Defenses in Federated Learning
Y Wen, J Geiping, M Goldblum, T Goldstein
ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023
22023
Seeing in Words: Learning to Classify through Language Bottlenecks
K Saifullah, Y Wen, J Geiping, M Goldblum, T Goldstein
Tiny Paper at ICLR 2023, 2023
12023
The system can't perform the operation now. Try again later.
Articles 1–20