firstbacksecondback
55 Results
|
Poster
|
RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models Zhuoran Jin · Pengfei Cao · Chenhao Wang · Zhitao He · Hongbang Yuan · Jiachun Li · Yubo Chen · Kang Liu · Jun Zhao |
||
|
Poster
|
Fri 16:30 |
Direct Unlearning Optimization for Robust and Safe Text-to-Image Models Yong-Hyun Park · Sangdoo Yun · Jin-Hwa Kim · Junho Kim · Geonhui Jang · Yonghyun Jeong · Junghyo Jo · Gayoung Lee |
|
|
Poster
|
Wed 16:30 |
UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models Yihua Zhang · Chongyu Fan · Yimeng Zhang · Yuguang Yao · Jinghan Jia · Jiancheng Liu · Gaoyuan Zhang · Gaowen Liu · Ramana Kompella · Xiaoming Liu · Sijia Liu |
|
|
Poster
|
Wed 11:00 |
Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement Zhehao Huang · Xinwen Cheng · JingHao Zheng · Haoran Wang · Zhengbao He · Tao Li · Xiaolin Huang |
|
|
Poster
|
Fri 11:00 |
Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models Yimeng Zhang · Xin Chen · Jinghan Jia · Yihua Zhang · Chongyu Fan · Jiancheng Liu · Mingyi Hong · Ke Ding · Sijia Liu |
|
|
Poster
|
Wed 11:00 |
Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference Jiabao Ji · Yujian Liu · Yang Zhang · Gaowen Liu · Ramana Kompella · Sijia Liu · Shiyu Chang |
|
|
Poster
|
Thu 16:30 |
UnSeg: One Universal Unlearnable Example Generator is Enough against All Image Segmentation Ye Sun · Hao Zhang · Tiehua Zhang · Xingjun Ma · Yu-Gang Jiang |
|
|
Poster
|
Thu 11:00 |
Large Language Model Unlearning Yuanshun Yao · Xiaojun Xu · Yang Liu |
|
|
Poster
|
Fri 11:00 |
Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness Weilin Lin · Li Liu · Shaokui Wei · Jianze Li · Hui Xiong |
|
|
Poster
|
Thu 16:30 |
Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space Leo Schwinn · David Dobre · Sophie Xhonneux · Gauthier Gidel · Stephan Günnemann |
|
|
Poster
|
Wed 11:00 |
What makes unlearning hard and what to do about it KAIRAN ZHAO · Meghdad Kurmanji · George-Octavian Bărbulescu · Eleni Triantafillou · Peter Triantafillou |
|
|
Affinity Event
|
LLM Unlearning EKG: Evaluations using Knowledge Graphs Rushali Mohbe · Samuel Scarpino |