Ruizhi Zhong — accepted AI-conference papers

2026

Jailbreaking Vision-Language Models via Dissonance-Guided Suffix Optimization and Image-Phrase Injection

Jiacheng Pi, Zhiguo Yang, Xingxing Huang, Dongsheng Xu, Ruizhi Zhong, Wenjie Ruan

CVPR 2026

The integration of vision and language in Vision-Language Models (VLMs), while enabling multimodal capabilities, inherently expands their attack surface. Among existing white-box jailbreak methods, suffix-optimization-based approaches often rely on gradient approximations over discrete token spaces,

Cited by 0 Source ↗code ↗Scholar ↗

2026

Logit-Margin Repulsion for Backdoor Defense

Zhiguo Yang, Dongsheng Xu, Ruizhi Zhong, Jiacheng Pi, Xingxing Huang, Wenjie Ruan

CVPR 2026

Backdoor attacks pose a significant threat to deep neural networks. Recent studies have shown that model compression, such as quantization and pruning, can be exploited by attackers to implant conditional backdoors. Such backdoors remain dormant in the original model but are activated after the mode

Cited by 0 Source ↗code ↗Scholar ↗