20 papers
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…
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…
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…
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…
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…
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…