Ruoxi Cheng
5 papers · 2025–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Cross-Pollinator (15) π Conference Polyglot (3) πΊοΈ Taxonomy Completionist (12) π§ Keyword Pioneer π Renaissance Researcher (5)
π
Interdisciplinary Bridge
β
Rising Star
(5)
β‘
Prolific Year
(5)
Conferences
NAACL (3)
COLING (1)
EMNLP (1)
Top co-authors
Research topics
Keywords
multimodal learning
(3)
toxicity maximization
(2)
adversarial perturbation
(2)
vision language model
(2)
large language model
(2)
membership inference
(2)
jailbreak attack
(2)
large vision language model
(2)
adversarial attack
(1)
black-box attack
(1)
adversarial prompt
(1)
privacy leakage
(1)
robustness evaluation
(1)
multimodal model
(1)
clip model
(1)
membership inference attack
(1)
cross-modal interaction
(1)
personal information
(1)
membership inference detection
(1)
audio-text model
(1)
Papers
SelfPrompt: Autonomously Evaluating LLM Robustness via Domain-Constrained Knowledge Guidelines and Refined Adversarial Prompts
COLING 2025
PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization
EMNLP 2025
TUNI: A Textual Unimodal Detector for Identity Inference in CLIP Models
NAACL 2025
Gibberish is All You Need for Membership Inference Detection in Contrastive Language-Audio Pretraining
NAACL 2025
PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization
NAACL 2025