paper-with-me

홈 › Papers

REFORGE: Multi-modal Attacks Reveal Vulnerable Concept Unlearning in Image Generation Models

2026-03-17 · Yong Zou, Haoran Li, Fanxiao Li, Shenyang Wei, Yunyun Dong, Li Tang, Wei Zhou, Renyang Liu arxiv

Recent progress in image generation models (IGMs) enables high-fidelity content creation but also amplifies risks, including the reproduction of copyrighted content and the generation of offensive content. Image Generation Model Unlearning (IGMU) mitigates these risks by removing harmful concepts without full retraining. Despite growing attention, the robustness under adversarial inputs, particularly image-side threats in black-box settings, remains underexplored. To bridge this gap, we present REFORGE, a black-box red-teaming framework that evaluates IGMU robustness via adversarial image prompts. REFORGE initializes stroke-based images and optimizes perturbations with a cross-attention-guided masking strategy that allocates noise to concept-relevant regions, balancing attack efficacy and visual fidelity. Extensive experiments across representative unlearning tasks and defenses demonstrate that REFORGE significantly improves attack success rate while achieving stronger semantic alignment and higher efficiency than involved baselines. These results expose persistent vulnerabilities in current IGMU methods and highlight the need for robustness-aware unlearning against multi-modal adversarial attacks. Our code is at: https://github.com/Imfatnoily/REFORGE.

📄 PDF Abstract BibTeX arXiv:2603.16576

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Similar Papers 제목 키워드 기반

Quantifying and Enhancing Multi-modal Robustness with Modality Preference

2024-02-09 · Zequn Yang, Yake Wei, Ce Liang, Di Hu

Multi-modal models have shown a promising capability to effectively integrate information from various sources, yet meanwhile, they are found vulnerable to pervasive perturbations, such as uni-modal attacks and missing c…

SecureForge: Finding and Preventing Vulnerabilities in LLM-Generated Code via Prompt Optimization

2026-05-08 · Houjun Liu, Lisa Einstein, John Yang, Joachim Baumann 외 arxiv

LLM coding agents now generate code at an unprecedented scale, yet LLM-generated code introduces cybersecurity vulnerabilities into codebases without human involvement. Even when frontier models are explicitly asked to w…

FeatureForge: A Novel Tool for Visually Supported Feature Engineering and Corpus Revision

2012-12-01 · COLING 2012 12 · Florian Heimerl, Charles Jochim, Steffen Koch, Thomas Ertl
Feature Engineering

Can LLMs Build a MaxSAT Solver from Papers? The CoreForge Experience

2026-07-16 · Ruben Martins arxiv

We report on CoreForge, an experience in using large language models (LLMs) to build an unweighted MaxSAT solver from research papers rather than from an existing solver codebase. The project focuses on unsatisfiability-…

Data Poisoning Attacks Against Multimodal Encoders

2022-09-30 · Ziqing Yang, Xinlei He, Zheng Li, Michael Backes 외

Recently, the newly emerged multimodal models, which leverage both visual and linguistic modalities to train powerful encoders, have gained increasing attention. However, learning from a large-scale unlabeled dataset als…

Contrastive LearningData Poisoning