Invisible Safety Threat: Malicious Finetuning for LLM via Steganography

Documenti analoghi

• Self-Purification Mitigates Backdoors in Multimodal Diffusion Language Models
  di: Wan, Guangnian, et al.
  Pubblicazione: (2026)
• CoT-Valve: Length-Compressible Chain-of-Thought Tuning
  di: Ma, Xinyin, et al.
  Pubblicazione: (2025)
• Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching
  di: Ma, Xinyin, et al.
  Pubblicazione: (2024)
• TinyFusion: Diffusion Transformers Learned Shallow
  di: Fang, Gongfan, et al.
  Pubblicazione: (2024)
• VeriThinker: Learning to Verify Makes Reasoning Model Efficient
  di: Chen, Zigeng, et al.
  Pubblicazione: (2025)