20 citations · 56 across the 24 of their papers we have counts for
22 papers · 1 filter
Preemptive LLM Unlearning against Forbidden Capability Acquisition via Gradient Sealing
Kemou Li, Qizhou Wang, Yue Wang +6
Open-weight LLMs are released not only as fixed products but also as substrates for downstream fine-tuning. This openness, however, creates legal and ethical risks because users ma…
Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning
Puning Yang, Junchi Yu, Qizhou Wang +3
Mitigating sensitive and harmful outputs is fundamental to ensuring safe deployment of LLMs. Existing approaches typically follow two paradigms: Knowledge Deletion (KD), which eras…
Graph Federated Unlearning for Privacy Preservation
Ruotong Ma, Wentao Yu, Qizhou Wang +2
Graph federated learning (GFL) facilitates decentralized training on distributed graph data while keeping sensitive user information local, aligning with policies such as GDPR and…
AEGIS: Adversarial Target-Guided Retention-Data-Free Robust Concept Erasure from Diffusion Models
Fengpeng Li, Kemou Li, Qizhou Wang +2
Concept erasure helps stop diffusion models (DMs) from generating harmful content; but current methods face robustness retention trade off. Robustness means the model fine-tuned by…
Explainable LLM Unlearning Through Reasoning
Junfeng Liao, Qizhou Wang, Shanshan Ye +3
LLM unlearning is essential for mitigating safety, copyright, and privacy concerns in pre-trained large language models (LLMs). Compared to preference alignment, it offers a more e…
Is Gradient Ascent Really Necessary? Memorize to Forget for Machine Unlearning
Zhuo Huang, Qizhou Wang, Ziming Hong +3
For ethical and safe AI, machine unlearning rises as a critical topic aiming to protect sensitive, private, and copyrighted knowledge from misuse. To achieve this goal, it is commo…
Understanding Negative Learning in Large Language Model Fine-tuning
Yue Wang, Qizhou Wang, Zizhuo Zhang +3
Negative learning has never been more important than it is today, particularly in large language model (LLM) fine-tuning, where it underpins machine unlearning, preference- and rew…
LLM Unlearning with LLM Beliefs
Kemou Li, Qizhou Wang, Yue Wang +4
Large language models trained on vast corpora inherently risk memorizing sensitive or harmful content, which may later resurface in their outputs. Prevailing unlearning methods gen…
Towards Understanding Valuable Preference Data for Large Language Model Alignment
Zizhuo Zhang, Qizhou Wang, Shanshan Ye +4
Large language model (LLM) alignment is typically achieved through learning from human preference comparisons, making the quality of preference data critical to its success. Existi…
Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning
Puning Yang, Qizhou Wang, Zhuo Huang +3
Loss reweighting has shown significant benefits for machine unlearning with large language models (LLMs). However, their exact functionalities are left unclear and the optimal stra…
GRU: Mitigating the Trade-off between Unlearning and Retention for LLMs
Yue Wang, Qizhou Wang, Feng Liu +4
Large language model (LLM) unlearning has demonstrated its essential role in removing privacy and copyright-related responses, crucial for their legal and safe applications. Howeve…
Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond
Qizhou Wang, Jin Peng Zhou, Zhanke Zhou +3
Large language models (LLMs) should undergo rigorous audits to identify potential risks, such as copyright and privacy infringements. Once these risks emerge, timely updates are cr…
Towards Effective Evaluations and Comparisons for LLM Unlearning Methods
Qizhou Wang, Bo Han, Puning Yang +3
The imperative to eliminate undesirable data memorization underscores the significance of machine unlearning for large language models (LLMs). Recent research has introduced a seri…
Learning to Augment Distributions for Out-of-Distribution Detection
Qizhou Wang, Zhen Fang, Yonggang Zhang +3
Open-world classification systems should discern out-of-distribution (OOD) data whose labels deviate from those of in-distribution (ID) cases, motivating recent studies in OOD dete…
Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sources
Haotian Zheng, Qizhou Wang, Zhen Fang +4
Out-of-distribution (OOD) detection discerns OOD data where the predictor cannot make valid predictions as in-distribution (ID) data, thereby increasing the reliability of open-wor…
Mixture Data for Training Cannot Ensure Out-of-distribution Generalization
Songming Zhang, Yuxiao Luo, Qizhou Wang +4
Deep neural networks often face generalization problems to handle out-of-distribution (OOD) data, and there remains a notable theoretical gap between the contributing factors and t…
Out-of-distribution Detection with Implicit Outlier Transformation
Qizhou Wang, Junjie Ye, Feng Liu +5
Outlier exposure (OE) is powerful in out-of-distribution (OOD) detection, enhancing detection capability via model fine-tuning with surrogate OOD data. However, surrogate data typi…
Watermarking for Out-of-distribution Detection
Qizhou Wang, Feng Liu, Yonggang Zhang +4
Out-of-distribution (OOD) detection aims to identify OOD data based on representations extracted from well-trained deep models. However, existing methods largely ignore the reprogr…
Towards Lightweight Black-Box Attacks against Deep Neural Networks
Chenghao Sun, Yonggang Zhang, Wan Chaoqun +5
Black-box attacks can generate adversarial examples without accessing the parameters of target model, largely exacerbating the threats of deployed deep neural networks (DNNs). Howe…
Probabilistic Margins for Instance Reweighting in Adversarial Training
Qizhou Wang, Feng Liu, Bo Han +5
Reweighting adversarial data during training has been recently shown to improve adversarial robustness, where data closer to the current decision boundaries are regarded as more cr…
Learning with Group Noise
Qizhou Wang, Jiangchao Yao, Chen Gong +4
Machine learning in the context of noise is a challenging but practical setting to plenty of real-world applications. Most of the previous approaches in this area focus on the pair…
Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model
Qizhou Wang, Bo Han, Tongliang Liu +3
The drastic increase of data quantity often brings the severe decrease of data quality, such as incorrect label annotations, which poses a great challenge for robustly training Dee…