Papers
1–3 of 3Research Paper·Feb 16, 2026
Weight space Detection of Backdoors in LoRA Adapters
LoRA adapters let users fine-tune large language models (LLMs) efficiently. However, LoRA adapters are shared through open repositories like Hugging Face Hub \citep{huggingface_hub_docs}, making them ...
6.0 viability
Research Paper·Feb 8, 2026
Robustness of Vision Language Models Against Split-Image Harmful Input Attacks
Vision-Language Models (VLMs) are now a core part of modern AI. Recent work proposed several visual jailbreak attacks using single/ holistic images. However, contemporary VLMs demonstrate strong robus...
5.0 viability
Research Paper·Feb 2, 2026
Backdoor Sentinel: Detecting and Detoxifying Backdoors in Diffusion Models via Temporal Noise Consistency
Diffusion models have been widely deployed in AIGC services; however, their reliance on opaque training data and procedures exposes a broad attack surface for backdoor injection. In practical auditing...
3.0 viability