Papers with Code 아카이브
input filtering
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Input filtering aims to filter out input data that is not necessary for executing model inference, thus reducing data transmission and computing overhead.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Concept Enhancement Engineering: A Lightweight and Efficient Robust Defense Against Jailbreak Attacks in Embodied AI
PiCo: Jailbreaking Multimodal Large Language Models via $\textbf{Pi}$ctorial $\textbf{Co}$de Contextualization
FLAME: Flexible LLM-Assisted Moderation Engine
Damage detection in an uncertain nonlinear beam based on stochastic Volterra series
Streamline tractography of the fetal brain in utero with machine learning
Signed-Prompt: A New Approach to Prevent Prompt Injection Attacks Against LLM-Integrated Applications
A novel efficient Multi-view traffic-related object detection framework
InFi: End-to-End Learning to Filter Input for Resource-Efficiency in Mobile-Centric Inference
Towards Effective and Robust Neural Trojan Defenses via Input Filtering
Stochastic-Shield: A Probabilistic Approach Towards Training-Free Adversarial Defense in Quantized CNNs
Real-time Classification from Short Event-Camera Streams using Input-filtering Neural ODEs
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.