activity
20182026
most citedPerturbations are not Enough: Generating Adversarial Examples with Spatial Distortions

3 citations · 5 across the 11 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2025

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…

cs.LG2025

Mitigating Semantic Collapse in Generative Personalization with Test-Time Embedding Adjustment

Anh Bui, Trang Vu, Trung Le +5

In this paper, we investigate the semantic collapsing problem in generative personalization, an under-explored topic where the learned visual concept () gradually shifts from it…

cs.LG2025

Fantastic Targets for Concept Erasure in Diffusion Models and Where To Find Them

Anh Bui, Trang Vu, Long Vuong +5

Concept erasure has emerged as a promising technique for mitigating the risk of harmful content generation in diffusion models by selectively unlearning undesirable concepts. The c…

cs.LG2024

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…

cs.LG2024

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…

cs.LG2020

Improving Adversarial Robustness by Enforcing Local and Global Compactness

Anh Bui, Trung Le, He Zhao +4

The fact that deep neural networks are susceptible to crafted perturbations severely impacts the use of deep learning in certain domains of application. Among many developed defens…