Given the brittle nature of existing methods in unlearning harmful content in diffusion models, we propose TRuST, a novel approach for dynamically estimating target concept neurons and unlearning them by selectively fine-tuning
Text guided diffusion models are used by millions of users, but can be easily exploited to produce harmful content. Concept unlearning methods aim at reducing the models' likelihood of generating harmful content. Traditionally, this has been tackled at an individual concept level, with only a handful of recent works considering more realistic concept combinations. However, state of the art methods depend on full finetuning, which is computationally expensive. Concept localisation methods can facilitate selective finetuning, but existing techniques are static, resulting in suboptimal utility. In order to tackle these challenges, we propose TRUST (Targeted Robust Selective fine Tuning), a novel approach for dynamically estimating target concept neurons and unlearning them through selective finetuning, empowered by a Hessian based regularization. We show experimentally, against a number of SOTA baselines, that TRUST is robust against adversarial prompts, preserves generation quality to a significant degree, and is also significantly faster than the SOTA. Our method achieves unlearning of not only individual concepts but also combinations of concepts and conditional concepts, without any specific regularization.
Selective Forgetting: Advancing Machine Unlearning Techniques and Evaluation in Language Models
Harbin Institute of Technology(哈尔滨工业大学);Huawei Noah’s Ark Lab(华为诺亚方舟实验室);Unlimidata Ltd(Unlimidata有限公司);The Chinese University of Hong Kong(香港中文大学);University of Calabria(卡拉布里亚大学)
Data-Free Privacy-Preserving for LLMs via Model Inversion and Selective Unlearning
School of Software Technology, Zhejiang University(浙江大学软件技术学院);Zhejiang University(浙江大学);Hefei University of Technology(合肥工业大学);Institute of Fundamental and Transdisciplinary Research, Zhejiang University(浙江大学基础与交叉学科研究院);Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security(杭州高新技术区(滨江区)区块链与数据安全研究院);The State Key Laboratory of Blockchain and Data Security(区块链与数据安全国家重点实验室);Zhejiang Key Laboratory of Big Data Intelligent Computing(浙江省大数据智能计算重点实验室)
Mechanism-Guided Selective Unlearning for RLVR-Induced Reasoning
School of Engineering, Institute of Science Tokyo, Japan(东京科学研究院工程学院);College of Control Science and Engineering, Zhejiang University, China(浙江大学控制科学与工程学院);Department of Electrical and Computer Engineering, National University of Singapore, Singapore(新加坡国立大学电子与计算机工程系)
Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearning
Hefei University of Technology(合肥工业大学);Institute of Artificial Intelligence, Hefei Comprehensive National Science Center(合肥综合性国家科学中心人工智能研究院);University of Amsterdam(阿姆斯特丹大学)
Beyond Superficial Unlearning: Sharpness-Aware Robust Erasure of Hallucinations in Multimodal LLMs
College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics(南京航空航天大学计算机科学与技术学院);Institute for AI, Tsinghua University(清华大学人工智能研究院);Huzhou University(湖州大学);Institute of Dataspace, Hefei Comprehensive National Science Center(合肥综合性国家科学中心数据空间研究院);University of Science and Technology of China(中国科学技术大学)
Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research
The GenLaw Center(GenLaw中心);Microsoft Research(微软研究院);Stanford University(斯坦福大学);Google DeepMind(谷歌DeepMind);Center for Democracy & Technology(民主与科技中心);Princeton(普林斯顿);Google(谷歌);University of Washington(华盛顿大学);University of Michigan(密歇根大学);Cornell Tech(康奈尔科技);Cornell Law School(康奈尔法学院);Cornell University(康奈尔大学);Lighthouse;Stanford Law School(斯坦福法学院);UC Berkeley(伯克利大学);Independent(独立研究者);Northeastern University(东北大学);Harvard Business School(哈佛商学院);W. Virginia University College of Law(维珍尼亚大学法学院)
OFFSIDE: Benchmarking Unlearning Misinformation in Multimodal Large Language Models
Harbin Institute of Technology(哈尔滨工业大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));BIAI, ZJUT & D5Data.ai(BIAI、浙江工业大学及D5Data.ai);National University of Singapore(新加坡国立大学)
Machine unlearning through fine-grained model parameters perturbation
College of Computer Science and Electronic Engineering, Hunan University(湖南大学计算机与电子工程学院);College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院);Shenzhen Research Institute, Hunan University(湖南大学深圳研究院);Faculty of Computing, Engineering & Media, De Montfort University(德蒙福特大学计算、工程与媒体学院)
Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs
Dept. of Computer Science & Munich Data Science Institute, Technical University of Munich(计算机科学系及慕尼黑数据科学研究所,技术大学慕尼黑);Mila, Université de Montréal(蒙特利尔大学Mila)
Machine Unlearning in Hyperbolic vs. Euclidean Multimodal Contrastive Learning: Adapting Alignment Calibration to MERU
Aalborg University(奥尔堡大学);University of Barcelona(巴塞罗那大学);Computer Vision Center(计算机视觉中心);Milestone Systems(里程碑系统公司);Pioneer Center for Artificial Intelligence(先锋人工智能中心)
Hierarchical Dual-Strategy Unlearning for Biomedical and Healthcare Intelligence Using Imperfect and Privacy-Sensitive Medical Data
Department of Neurosurgery, Qilu Hospital of Shandong University and Institute of Brain and Brain-Inspired Science(齐鲁医院山东大学神经外科和脑科学与脑启发科学研究院);Department of Neurosurgery, The Affiliated Hospital of Qingdao University(青岛大学附属医院神经外科);Department of Neurosurgery, Peking Union Medical College Hospital(北京地坛医院神经外科);School of Software and Microelectronics, Peking University(北京大学软件与微电子学院);College of Artificial Intelligence, Dalian Maritime University(大连海事大学人工智能学院);University of Colorado Boulder(科罗拉多大学波尔德分校);Zhengzhou University(郑州大学);The University of Hong Kong(香港大学);Georgia Institute of Technology(佐治亚理工学院)