activity
20242026
collaborators

7 papers

cs.CR2026

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…

cs.CV2025

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…

cs.CR2025

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…

cs.CL2025

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…

cs.CV2024

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…

cs.CR2024

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…