4 papers
Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks
Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu +1
With the growing adoption of VLMs, DMs, LLMs, and AFMs, these multimodal foundation models can inadvertently encode sensitive, copyrighted, biased, or unsafe cross-modal associatio…
Certified but Fooled! Breaking Certified Defences with Ghost Certificates
Quoc Viet Vo, Tashreque M. Haq, Paul Montague +3
Certified defenses promise provable robustness guarantees. We study the malicious exploitation of probabilistic certification frameworks to better understand the limits of guarante…
Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation
Anh Bui, Long Vuong, Khanh Doan +4
Diffusion models excel at generating visually striking content from text but can inadvertently produce undesirable or harmful content when trained on unfiltered internet data. A pr…
Hiding and Recovering Knowledge in Text-to-Image Diffusion Models via Learnable Prompts
Anh Bui, Khanh Doan, Trung Le +3
Diffusion models have demonstrated remarkable capability in generating high-quality visual content from textual descriptions. However, since these models are trained on large-scale…