Skip to content
conftrace_

stealthiness

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

cold-attack (1) controllable attack generation (1) sentiment (1) semantic-enhancing learning (1) sphere-probing learning (1) heterogeneous triggers (1) poisoned image pairs (1) bridge direction (1) jailbreak (1) backdoor (1)

Papers

MixBridge: Heterogeneous Image-to-Image Backdoor Attack through Mixture of Schrödinger Bridges ICML 2025 TtBA: Two-third Bridge Approach for Decision-Based Adversarial Attack ICML 2025 COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability ICML 2024 UPAM: Unified Prompt Attack in Text-to-Image Generation Models Against Both Textual Filters and Visual Checkers ICML 2024