activity
20242026
collaborators

5 papers

cs.LG2026

Consistency Training Along the Transformer Stack

Sukrati Gautam, Neil Shah, Arav Dhoot +7

Consistency training encourages models to behave similarly across different contexts, and has shown promise for reducing misalignment. We broaden the scope of consistency training…

cs.CV2026

Hierarchical Refinement of Universal Multimodal Attacks on Vision-Language Models

Peng-Fei Zhang, Zi Huang

Existing adversarial attacks for VLP models are mostly sample-specific, resulting in substantial computational overhead when scaled to large datasets or new scenarios. To overcome…

cs.LG2025

GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generation

Danny Wang, Ruihong Qiu, Guangdong Bai +1

Despite graph neural networks' (GNNs) great success in modelling graph-structured data, out-of-distribution (OOD) test instances still pose a great challenge for current GNNs. One…

cs.CV2025

MAA: Meticulous Adversarial Attack against Vision-Language Pre-trained Models

Peng-Fei Zhang, Guangdong Bai, Zi Huang

Current adversarial attacks for evaluating the robustness of vision-language pre-trained (VLP) models in multi-modal tasks suffer from limited transferability, where attacks crafte…

cs.CV2024

Universal Adversarial Perturbations for Vision-Language Pre-trained Models

Peng-Fei Zhang, Zi Huang, Guangdong Bai

Vision-language pre-trained (VLP) models have been the foundation of numerous vision-language tasks. Given their prevalence, it becomes imperative to assess their adversarial robus…