6 papers
Membership Inference for Contrastive Pre-training Models with Text-only PII Queries
Ruoxi Cheng, Yizhong Ding, Jian Zhao +5
Contrastive pretraining models such as CLIP and CLAP, serve as the ubiquitous perceptual backbones for modern multimodal large models, yet their reliance on web-scale data raises g…
ShellForge: Adversarial Co-Evolution of Webshell Generation and Multi-View Detection for Robust Webshell Defense
Yizhong Ding
Webshells remain a primary foothold for attackers to compromise servers, particularly within PHP ecosystems. However, existing detection mechanisms often struggle to keep pace with…
AutoVulnPHP: LLM-Powered Two-Stage PHP Vulnerability Detection and Automated Localization
Zhiqiang Wang, Yizhong Ding, Zilong Xiao +3
PHP's dominance in web development is undermined by security challenges: static analysis lacks semantic depth, causing high false positives; dynamic analysis is computationally exp…
PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization
Ruoxi Cheng, Yizhong Ding, Shuirong Cao +6
Understanding the vulnerabilities of Large Vision Language Models (LVLMs) to jailbreak attacks is essential for their responsible real-world deployment. Most previous work requires…
A Reward-driven Automated Webshell Malicious-code Generator for Red-teaming
Yizhong Ding
Frequent cyber-attacks have elevated WebShell exploitation and defense to a critical research focus within network security. However, there remains a significant shortage of public…
Gibberish is All You Need for Membership Inference Detection in Contrastive Language-Audio Pretraining
Ruoxi Cheng, Yizhong Ding, Shuirong Cao +2
Audio can disclose PII, particularly when combined with related text data. Therefore, it is essential to develop tools to detect privacy leakage in Contrastive Language-Audio Pretr…