 ForgetMe: Evaluating Selective Forgetting in Generative ModelsEngineering applications of artificial intelligence (EAAI), 2025 |
 Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation ModelsIEEE Symposium on Security and Privacy (S&P), 2024 |
 Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion ModelsNorth American Chapter of the Association for Computational Linguistics (NAACL), 2024 |
 MACE: Mass Concept Erasure in Diffusion ModelsComputer Vision and Pattern Recognition (CVPR), 2024 |
 Unified Concept Editing in Diffusion ModelsIEEE Workshop/Winter Conference on Applications of Computer Vision (WACV), 2023 |
 Ticketed Learning-Unlearning SchemesAnnual Conference Computational Learning Theory (COLT), 2023 |
 LEACE: Perfect linear concept erasure in closed formNeural Information Processing Systems (NeurIPS), 2023 |
 SneakyPrompt: Jailbreaking Text-to-image Generative ModelsIEEE Symposium on Security and Privacy (IEEE S&P), 2023 |
 Extracting Training Data from Diffusion ModelsUSENIX Security Symposium (USENIX Security), 2023 |
 Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning AttacksNeural Information Processing Systems (NeurIPS), 2022 |
 Algorithms that Approximate Data Removal: New Results and LimitationsNeural Information Processing Systems (NeurIPS), 2022 |
 The Privacy Onion Effect: Memorization is RelativeNeural Information Processing Systems (NeurIPS), 2022 |
 High-Resolution Image Synthesis with Latent Diffusion ModelsComputer Vision and Pattern Recognition (CVPR), 2021 |
 Talk-to-Edit: Fine-Grained Facial Editing via DialogIEEE International Conference on Computer Vision (ICCV), 2021 |
 LoRA: Low-Rank Adaptation of Large Language ModelsInternational Conference on Learning Representations (ICLR), 2021 |
 Adaptive Machine UnlearningNeural Information Processing Systems (NeurIPS), 2021 |
 Remember What You Want to Forget: Algorithms for Machine UnlearningNeural Information Processing Systems (NeurIPS), 2021 |
 When Machine Unlearning Jeopardizes PrivacyConference on Computer and Communications Security (CCS), 2020 |
 Machine UnlearningIEEE Symposium on Security and Privacy (IEEE S&P), 2019 |
 Large Scale Incremental LearningComputer Vision and Pattern Recognition (CVPR), 2019 |
 Parameter-Efficient Transfer Learning for NLPInternational Conference on Machine Learning (ICML), 2019 |
 Progressive Growing of GANs for Improved Quality, Stability, and
VariationInternational Conference on Learning Representations (ICLR), 2017 |
 Microsoft COCO: Common Objects in ContextEuropean Conference on Computer Vision (ECCV), 2014 |
