Performance Analysis
Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration
Membership Inference Attacks (MIA) aim to infer whether a target data record has been utilized for model training or not.
Attack-A ware Noise Calibration for Differential Privacy
Differential privacy (DP) is a widely used approach for mitigating privacy risks when training machine learning models on sensitive data. DP mechanisms add noise during training to limit the risk of information leakage. The scale of the added noise is critical, as it determines the trade-off between privacy and utility.
A Benchmark Dataset for Event-Guided Human Pose Estimation and Tracking in Extreme Conditions
Multi-person pose estimation and tracking have been actively researched by the computer vision community due to their practical applicability. However, existing human pose estimation and tracking datasets have only been successful in typical scenarios, such as those without motion blur or with well-lit conditions.
Semantic Density: Uncertainty Quantification for Large Language Models through Confidence Measurement in Semantic Space
A new framework is proposed in this paper to address these issues.
Kernel PCA for Out-of-Distribution Detection Kun Fang
Out-of-Distribution (OoD) detection is vital for the reliability of Deep Neural Networks (DNNs).
ChronoEpilogi: Scalable Time-Series Variable Selection with Multiple Solutions
Lasso performance, with the added benefit of providing multiple solutions.
Detecting Bugs with Substantial Monetary Consequences by LLM and Rule-based Reasoning
According to a recent study, accounting bugs (i.e., incorrect implementations of domain-specific financial models) are the most prevalent type of vulnerability, and are one of the most difficult to find,
CODE: Contrasting Self-generated Description to Combat Hallucination in Large Multi-modal Models Junho Kim Hyun Jun Kim Y eon Ju Kim Yong Man Ro
Large Multi-modal Models (LMMs) have recently demonstrated remarkable abilities in visual context understanding and coherent response generation.