7 papers
Seeking Flat Minima over Diverse Surrogates for Improved Adversarial Transferability: A Theoretical Framework and Algorithmic Instantiation
Meixi Zheng, Kehan Wu, Yanbo Fan +2
The transfer-based black-box adversarial attack setting poses the challenge of crafting an adversarial example (AE) on known surrogate models that remain effective against unseen t…
FauForensics: Boosting Audio-Visual Deepfake Detection with Facial Action Units
Jian Wang, Baoyuan Wu, Li Liu +1
The rapid evolution of generative AI has increased the threat of realistic audio-visual deepfakes, demanding robust detection methods. Existing solutions primarily address unimodal…
BlackboxBench: A Comprehensive Benchmark of Black-box Adversarial Attacks
Meixi Zheng, Xuanchen Yan, Zihao Zhu +2
Adversarial examples are well-known tools to evaluate the vulnerability of deep neural networks (DNNs). Although lots of adversarial attack algorithms have been developed, it's sti…
To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models
Zihao Zhu, Hongbao Zhang, Ruotong Wang +3
Large Reasoning Models (LRMs) are designed to solve complex tasks by generating explicit reasoning traces before producing final answers. However, we reveal a critical vulnerabilit…
HMGIE: Hierarchical and Multi-Grained Inconsistency Evaluation for Vision-Language Data Cleansing
Zihao Zhu, Hongbao Zhang, Guanzong Wu +2
Visual-textual inconsistency (VTI) evaluation plays a crucial role in cleansing vision-language data. Its main challenges stem from the high variety of image captioning datasets, w…
WPDA: Frequency-based Backdoor Attack with Wavelet Packet Decomposition
Zhengyao Song, Yongqiang Li, Danni Yuan +3
This work explores an emerging security threat against deep neural networks (DNNs) based image classification, i.e., backdoor attack. In this scenario, the attacker aims to inject…