firstbacksecondback
14 Results
|
Workshop
|
Semantic Membership Inference Attack against Large Language Models Hamid Mozaffari · Virendra Marathe |
||
|
Workshop
|
Semantic Membership Inference Attack against Large Language Models Hamid Mozaffari · Virendra Marathe |
||
|
Poster
|
Thu 16:30 |
OSLO: One-Shot Label-Only Membership Inference Attacks Yuefeng Peng · Jaechul Roh · Subhransu Maji · Amir Houmansadr |
|
|
Poster
|
Wed 16:30 |
Membership Inference Attacks against Large Vision-Language Models Zhan Li · Yongtao Wu · Yihang Chen · Francesco Tonin · Elias Abad Rocamora · Volkan Cevher |
|
|
Workshop
|
Unveiling Synthetic Faces: How Synthetic Datasets Can Expose Real Identities Hatef Otroshi Shahreza · Sébastien Marcel |
||
|
Poster
|
Fri 11:00 |
Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration Wenjie Fu · Huandong Wang · Chen Gao · Guanghua Liu · Yong Li · Tao Jiang |
|
|
Workshop
|
Sat 12:00 |
Infilling Score: A Pretraining Data Detection Algorithm for Large Language Models Negin Raoof · Litu Rout · Giannis Daras · Sujay Sanghavi · Constantine Caramanis · Sanjay Shakkottai · Alex Dimakis |
|
|
Workshop
|
Has My System Prompt Been Used? Large Language Model Prompt Membership Inference Roman Levin · Valeriia Cherepanova · Abhimanyu Hans · Avi Schwarzschild · Tom Goldstein |
||
|
Poster
|
Fri 16:30 |
Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy Shengfang ZHAI · Huanran Chen · Yinpeng Dong · Jiajun Li · Qingni Shen · Yansong Gao · Hang Su · Yang Liu |
|
|
Workshop
|
Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data? Michael-Andrei Panaitescu-Liess · Zora Che · Bang An · Yuancheng Xu · Pankayaraj Pathmanathan · Souradip Chakraborty · Sicheng Zhu · Tom Goldstein · Furong Huang |
||
|
Poster
|
Wed 11:00 |
Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models Yuxin Wen · Leo Marchyok · Sanghyun Hong · Jonas Geiping · Tom Goldstein · Nicholas Carlini |
|
|
Poster
|
Thu 16:30 |
Data Mixture Inference Attack: BPE Tokenizers Reveal Training Data Compositions Jonathan Hayase · Alisa Liu · Yejin Choi · Sewoong Oh · Noah Smith |