firstbacksecondback
41 Results
|
Poster
|
TrojText: Test-time Invisible Textual Trojan Insertion Qian Lou · Yepeng Liu · Bo Feng |
||
|
Poster
|
Tue 2:30 |
Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models Liam H Fowl · Jonas Geiping · Steven Reich · Yuxin Wen · Wojciech Czaja · Micah Goldblum · Tom Goldstein |
|
|
Poster
|
Tue 7:30 |
Incompatibility Clustering as a Defense Against Backdoor Poisoning Attacks Charles Jin · Melinda Sun · Martin Rinard |
|
|
Poster
|
Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning Hao He · Kaiwen Zha · Dina Katabi |
||
|
Poster
|
Effective passive membership inference attacks in federated learning against overparameterized models Jiacheng Li · Ninghui Li · Bruno Ribeiro |
||
|
Poster
|
Tue 2:30 |
Self-Ensemble Protection: Training Checkpoints Are Good Data Protectors Sizhe Chen · Geng Yuan · Xinwen Cheng · Yifan Gong · Minghai Qin · Yanzhi Wang · Xiaolin Huang |
|
|
Poster
|
Tue 2:30 |
CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning Samuel Maddock · Alexandre Sablayrolles · Pierre Stock |
|
|
Poster
|
Defending against Adversarial Audio via Diffusion Model Shutong Wu · Jiongxiao Wang · Wei Ping · Weili Nie · Chaowei Xiao |
||
|
Poster
|
Mon 7:30 |
Certifiably Robust Policy Learning against Adversarial Multi-Agent Communication Yanchao Sun · Ruijie Zheng · Parisa Hassanzadeh · Yongyuan Liang · Soheil Feizi · Sumitra Ganesh · Furong Huang |
|
|
Poster
|
Towards Robustness Certification Against Universal Perturbations Yi Zeng · Zhouxing Shi · Ming Jin · Feiyang Kang · Lingjuan Lyu · Cho-Jui Hsieh · Ruoxi Jia |
||
|
Poster
|
Revisiting the Assumption of Latent Separability for Backdoor Defenses Xiangyu Qi · Tinghao Xie · Yiming Li · Saeed Mahloujifar · Prateek Mittal |
||
|
Poster
|
Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense Mechanisms Linbo Liu · Youngsuk Park · Nghia Hoang · Hilaf Hasson · Jun Huan |