Xiaojun Jia
~Xiaojun_Jia1
10
论文总数
5.0
年均投稿
平均评分
接收情况6/10
会议分布
ICLR
6
NeurIPS
2
ICML
2
发表论文 (10 篇)
20259 篇
4
Improved Techniques for Optimization-Based Jailbreaking on Large Language Models
ICLR 2025Poster
4
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
NeurIPS 2025Poster
4
OT-Attack: Enhancing Adversarial Transferability of Vision-Language Models via Optimal Transport Optimization
ICLR 2025withdrawn
4
Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs
ICML 2025Poster
4
No Access, No Safety: Free Lunch Adversarial Attacks on Black-box NLP Models
ICLR 2025withdrawn
4
CleanerCLIP: Fine-grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning
ICLR 2025withdrawn
4
LLM Jailbreak Detection for (Almost) Free!
ICLR 2025withdrawn
3
DAMA: Data- and Model-aware Alignment of Multi-modal LLMs
ICML 2025Poster
4
SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAG
NeurIPS 2025Poster