Paper 13
- VLM 모델 대상 Adversarial Attack 연구 동향
- VLM 모델 대상 Membership Inference Attack 연구 동향
- LLM 모델 대상 Membership Inference Attack: 흐름과 최신 연구 동향
- VLM 모델의 흐름: From Alignment to Native Multimodal
- Is Difficulty Calibration All We Need? Towards More Practical Membership Inference Attacks
- FUSION: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding
- M4I: Multi-modal Models Membership Inference
- AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Models
- AdvLogo: Adversarial Patch Attack against Object Detectors based on Diffusion Models
- Scalable Diffusion Models with Transformers
- Don't trust your eyes: on the (un)reliability of feature visualizations
- Please Tell Me More: Privacy Impact of Explainability through the Lens of Membership Inference Attack
- DeepSeek-R1 : Incentivizing Reasoning Capability in LLMs via Reinforcement Learning