Papers by Simeng Qin

2 papers
PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods to jailbreak Large Vision Language Models do not consider interaction between images and text.
Approach: They propose a prior-guided bimodal interactive black-box jailbreak attack for toxicity maximization that exploits the interaction of images and text.
Outcome: The proposed method outperforms state-of-the-art jailbreak methods in black box scenarios and in closed-source LVLMs.
Asymmetric Relational-Geometry Driven Universal Adversarial Perturbations for Vision-Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing universal adversarial perturbation (UAP) methods suffer from limited cross-model transferability in black-box scenarios.
Approach: They propose an optimization-based framework that learns universal perturbations under an asymmetric relational-geometry driven objective.
Outcome: The proposed framework outperforms state-of-the-art models in black-box transfer settings.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations