12 papers
LLM Persona Unlearning
Kemou Li, Zhuan Shi, Qizhou Wang +4
Pre-training equips large language models (LLMs) with a broad repertoire of behavioral patterns associated with roles, styles, values, and goals. Post-training teaches conditional…
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…
TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
Alireza Dehghanpour Farashah, Zhuan Shi, Negar Rostamzadeh +1
Text-to-image diffusion models can be misused to generate harmful content through adversarial or paraphrased prompts that bypass built-in safety mechanisms. Existing concept erasur…
IP Protection in the Era of Visual Generative AI: A Survey
Zhuan Shi, Shunchang Liu, Alireza Dehghanpour Farashah +8
The rapid evolution of visual generative AI has introduced a wide range of intellectual property risks, spanning the unauthorized learning, reproduction, extraction, misuse, and re…
How and What to Imagine? Visual Thinking in Unified Multimodal Models for Cross-View Spatial Reasoning
Qian Yang, Ankur Sikarwar, Huy Le +4
Cross-view spatial reasoning remains a weak spot for vision-language models (VLMs): they reason in language and discard the fine-grained geometry the task requires. Thinking with i…
Neighbor-Aware Localized Concept Erasure in Text-to-Image Diffusion Models
Zhuan Shi, Alireza Dehghanpour Farashah, Rik de Vries +1
Concept erasure in text-to-image diffusion models seeks to remove undesired concepts while preserving overall generative capability. Localized erasure methods aim to restrict edits…
Multilingual Amnesia: On the Transferability of Unlearning in Multilingual LLMs
Alireza Dehghanpour Farashah, Aditi Khandelwal, Marylou Fauchard +3
As multilingual large language models become more widely used, ensuring their safety and fairness across diverse linguistic contexts presents unique challenges. While existing rese…
Reviving Your MNEME: Predicting The Side Effects of LLM Unlearning and Fine-Tuning via Sparse Model Diffing
Aly M. Kassem, Zhuan Shi, Negar Rostamzadeh +1
Large language models (LLMs) are frequently fine-tuned or unlearned to adapt to new tasks or eliminate undesirable behaviors. While existing evaluation methods assess performance a…
FedCDC: A Collaborative Framework for Data Consumers in Federated Learning Market
Zhuan Shi, Patrick Ohl, Boi Faltings
Federated learning (FL) allows machine learning models to be trained on distributed datasets without directly accessing local data. In FL markets, numerous Data Consumers compete t…
CopyJudge: Automated Copyright Infringement Identification and Mitigation in Text-to-Image Diffusion Models
Shunchang Liu, Zhuan Shi, Lingjuan Lyu +2
Assessing whether AI-generated images are substantially similar to source works is a crucial step in resolving copyright disputes. In this paper, we propose CopyJudge, a novel auto…
Copyright-Aware Incentive Scheme for Generative Art Models Using Hierarchical Reinforcement Learning
Zhuan Shi, Yifei Song, Xiaoli Tang +2
Generative art using Diffusion models has achieved remarkable performance in image generation and text-to-image tasks. However, the increasing demand for training data in generativ…
RLCP: A Reinforcement Learning-based Copyright Protection Method for Text-to-Image Diffusion Model
Zhuan Shi, Jing Yan, Xiaoli Tang +2
The increasing sophistication of text-to-image generative models has led to complex challenges in defining and enforcing copyright infringement criteria and protection. Existing me…