firstbacksecondback
15 Results
|
Poster
|
Wed 11:00 |
From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models Zhuoshi Pan · Yuguang Yao · Gaowen Liu · Bingquan Shen · H. Vicky Zhao · Ramana Kompella · Sijia Liu |
|
|
Poster
|
Wed 16:30 |
RFLPA: A Robust Federated Learning Framework against Poisoning Attacks with Secure Aggregation Peihua Mai · Ran Yan · Yan Pang |
|
|
Poster
|
Fri 11:00 |
SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents Ethan Rathbun · Christopher Amato · Alina Oprea |
|
|
Poster
|
Fri 16:30 |
AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases Zhaorun Chen · Zhen Xiang · Chaowei Xiao · Dawn Song · Bo Li |
|
|
Poster
|
Thu 16:30 |
PureGen: Universal Data Purification for Train-Time Poison Defense via Generative Model Dynamics Omead Pooladzandi · Sunay Bhat · Jeffrey Jiang · Alexander Branch · Gregory Pottie |
|
|
Poster
|
Wed 11:00 |
Dual Defense: Enhancing Privacy and Mitigating Poisoning Attacks in Federated Learning Runhua Xu · Shiqi Gao · Chao Li · James Joshi · Jianxin Li |
|
|
Poster
|
Wed 11:00 |
Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models Yuancheng Xu · Jiarui Yao · Manli Shu · Yanchao Sun · Zichu Wu · Ning Yu · 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 |
|
|
Workshop
|
vTune: Verifiable Fine-Tuning Through Backdooring Eva Zhang · Akilesh Potti · Micah Goldblum |
||
|
Workshop
|
Mitigating Downstream Model Risks via Model Provenance Keyu Wang · Scott Schaffter · Abdullah Norozi Iranzad · Doina Precup · Jonathan Lebensold · Megan Risdal |
||
|
Workshop
|
Using Influence Functions to Unlearn Poisons Wenjie Li · Jiawei Li · Christian Schroeder de Witt · Ameya Prabhu · Amartya Sanyal |
||
|
Workshop
|
Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks Lukas Gosch · Mahalakshmi Sabanayagam · Debarghya Ghoshdastidar · Stephan Günnemann |