collaborators

20 papers

cs.CV2026

Robustifying Vision-Language Models via Test-Time Prompt Adaptation

Xingyu Zhu, Huanshen Wu, Shuo Wang +4

Pre-trained Vision-Language Models (VLMs) such as CLIP achieve strong zero-shot generalization, but their performance degrades sharply under adversarial perturbations. Existing tes…

cs.LG2026

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models

Yang Dai, Oubo Ma, Longfei Zhang +6

Recent advances in Trajectory Optimization (TO) models have achieved remarkable success in offline reinforcement learning. However, their vulnerabilities against backdoor attacks a…

cs.CR2026

SWAP: Towards Copyright Auditing of Soft Prompts via Sequential Watermarking

Wenyuan Yang, Yichen Sun, Changzheng Chen +4

Large-scale vision-language models, especially CLIP, have demonstrated remarkable performance across diverse downstream tasks. Soft prompts, as carefully crafted modules that effic…

cs.CR2026

BadDLM: Backdooring Diffusion Language Models with Diverse Targets

Shengfang Zhai, Xiaoyang Ji, Yuling Shi +6

Diffusion language models (DLMs) have recently emerged as an alternative modeling paradigm to autoregressive (AR) language models, enabling parallel generation and bidirectional co…

cs.AI2026

ReProbe: Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Models

Jingwei Ni, Ekaterina Fadeeva, Tianyi Wu +8

LLMs can solve complex tasks by generating long, multi-step reasoning chains. Test-time scaling (TTS) can further improve performance by sampling multiple variants of intermediate…

cs.CR2026

Hijacking Large Audio-Language Models via Context-Agnostic and Imperceptible Auditory Prompt Injection

Meng Chen, Kun Wang, Li Lu +2

Modern Large audio-language models (LALMs) power intelligent voice interactions by tightly integrating audio and text. This integration, however, expands the attack surface beyond…