Xiaoshuang Jia
4 papers · 2025–2026 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(10)
Top co-authors
Research topics
Keywords
jailbreak attack
(3)
multimodal learning
(2)
adversarial learning
(2)
adversarial attack
(2)
adversarial perturbation
(2)
vision-language model
(2)
large vision-language model
(2)
toxicity maximization
(2)
graph prompt learning
(1)
multimodal large language model
(1)
toxicity detection
(1)
multimodal risk distribution
(1)
cross-modal interaction
(1)
security vulnerability
(1)
topology recovery
(1)
bidirectional cross-modal interaction
(1)
greedy search optimization
(1)
bayesian estimation
(1)
privacy aware learning
(1)
large language model
(1)
Papers
PAGPL: Privacy-Aware Graph Prompt Learning Scheme via Adaptive Perturbation-Estimated Topology Recovery
AAAI 2026
Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models
ICCV 2025
PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization
EMNLP 2025
PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization
NAACL 2025