3 citations · 3 across the 8 of their papers we have counts for
9 papers
Visual Attention Faithfulness in Vision-Language Models is Heterogeneous
Xurui Song, Weishi Wang, Zhongqi Yue +5
Whether attention weights faithfully reflect model reasoning has been actively debated in NLP, yet this question remains largely unexplored for the visual modality in Vision-Langua…
TrojanPraise: Jailbreak LLMs via Benign Fine-Tuning
Zhixin Xie, Xurui Song, Jun Luo
The demand of customized large language models (LLMs) has led to commercial LLMs offering black-box fine-tuning APIs, yet this convenience introduces a critical security loophole:…
Attack via Overfitting: 10-shot Benign Fine-tuning to Jailbreak LLMs
Zhixin Xie, Xurui Song, Jun Luo
Despite substantial efforts in safety alignment, recent research indicates that Large Language Models (LLMs) remain highly susceptible to jailbreak attacks. Among these attacks, fi…
Cheating Stereo Matching in Full-scale: Physical Adversarial Attack against Binocular Depth Estimation in Autonomous Driving
Kangqiao Zhao, Shuo Huai, Xurui Song +1
Though deep neural models adopted to realize the perception of autonomous driving have proven vulnerable to adversarial examples, known attacks often leverage 2D patches and target…
More Than Meets the Eye? Uncovering the Reasoning-Planning Disconnect in Training Vision-Language Driving Models
Xurui Song, Shuo Huai, JingJing Jiang +2
Vision-Language Model (VLM) driving agents promise explainable end-to-end autonomy by first producing natural-language reasoning and then predicting trajectory planning. However, w…
Where to Start Alignment? Diffusion Large Language Model May Demand a Distinct Position
Zhixin Xie, Xurui Song, Jun Luo
Diffusion Large Language Models (dLLMs) have recently emerged as a competitive non-autoregressive paradigm due to their unique training and inference approach. However, there is cu…
Corvid: Improving Multimodal Large Language Models Towards Chain-of-Thought Reasoning
Jingjing Jiang, Chao Ma, Xurui Song +2
Recent advancements in multimodal large language models (MLLMs) have demonstrated exceptional performance in multimodal perception and understanding. However, leading open-source M…
Dagger Behind Smile: Fool LLMs with a Happy Ending Story
Xurui Song, Zhixin Xie, Shuo Huai +2
The wide adoption of Large Language Models (LLMs) has attracted significant attention from attacks, where adversarial prompts crafted through optimization or m…
Do Not DeepFake Me: Privacy-Preserving Neural 3D Head Reconstruction Without Sensitive Images
Jiayi Kong, Xurui Song, Shuo Huai +3
While 3D head reconstruction is widely used for modeling, existing neural reconstruction approaches rely on high-resolution multi-view images, posing notable privacy issues. Indivi…