Vision-language models (VLMs) exhibit strong multimodal capabilities but remain vulnerable to backdoors implanted through poisoned fine-tuning data. Existing defenses often require extensive parameter updates during fine-tuning or incur per-query overhead during inference. To address these limitations, we propose Pertu...
Large vision-language models (LVLMs) routinely use inference-time visual-token compression to prune hundreds of patch tokens down to a compact budget. Existing LVLM backdoors fire whenever a triggered image appears, whereas prior deployment-triggered attacks activate only when model weights are quantized or pruned. How...
Zhi-Fang Zhang, Qi-Rui Huang, Chen-Peng Wang et al.· 0 citations
OrthoPurify is proposed, a more efficient method to purify backdoored model weights via one-step orthogonal projection, which reduces the attack success rate to near zero while preserving the original performance across diverse benchmarks, without retraining the backdoored model or introducing inference-time overhead.
Bo Yang, Hao Zhou, Zhi-Fang Zhang et al.· 0 citations
AntiSkillBench is introduced, an end-to-end benchmark for evaluating risks and defenses across the persona-skill pipeline, and experiments show that persona-skill risks persist across agent backbones and distillation protocols, extending from explicit attributes to communication styles and personality traits.
Yongli Xiang, Zhi-Fang Zhang, Bojun Yang et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.