research-papers
Original Paper: https://arxiv.org/abs/2312.08317 By: Pei Yan, Shunquan Tan, Miaohui Wang, Jiwu Huang Abstract: Dynamic analysis methods effectively identify shelled, wrapped, or obfuscated malware, thereby preventing them from invading computers. As a significant representation of dynamic malware behavior, the API (Application Programming Interface) sequence, comprised of
research-papers
Original Paper: https://arxiv.org/abs/2312.11513 By: Ahmed Salem, Andrew Paverd, Boris Köpf Abstract: Prompt injection has emerged as a serious security threat to large language models (LLMs). At present, the current best-practice for defending against newly-discovered prompt injection techniques is to add additional guardrails to the system
research-papers
Original Paper: https://arxiv.org/abs/2312.04344 By: Pengcheng Chen, Ziyan Huang, Zhongying Deng, Tianbin Li, Yanzhou Su, Haoyu Wang, Jin Ye, Yu Qiao, Junjun He Abstract: OpenAI's latest large vision-language model (LVLM), GPT-4V(ision), has piqued considerable interest for its potential in medical applications. Despite its
research-papers
Original Paper: https://arxiv.org/abs/2311.06062 By: Wenjie Fu, Huandong Wang, Chen Gao, Guanghua Liu, Yong Li, Tao Jiang Abstract: Membership Inference Attacks (MIA) aim to infer whether a target data record has been utilized for model training or not. Prior attempts have quantified the privacy risks of
research-papers
Original Paper: https://arxiv.org/abs/2312.05180 By: Olga Golovneva, Sean O'Brien, Ramakanth Pasunuru, Tianlu Wang, Luke Zettlemoyer, Maryam Fazel-Zarandi, Asli Celikyilmaz Abstract: With recent advancements in large language models, methods like chain-of-thought prompting to elicit reasoning chains have been shown to improve results on reasoning tasks.
research-papers
Original Paper: https://arxiv.org/abs/2312.06185 By: Qinggang Zhang, Junnan Dong, Hao Chen, Daochen Zha, Zailiang Yu, Xiao Huang Abstract: Generative Large Language Models (LLMs), such as ChatGPT, offer interactive APIs that can answer common questions at a human-expert level. However, these models often give inaccurate or incorrect
research-papers
Original Paper: https://arxiv.org/abs/2312.06660 By: Chong Zhou, Xiangtai Li, Chen Change Loy, Bo Dai Abstract: This paper presents EdgeSAM, an accelerated variant of the Segment Anything Model (SAM), optimized for efficient execution on edge devices with minimal compromise in performance. Our approach involves distilling the original
research-papers
Original Paper: https://arxiv.org/abs/2311.15317 By: Xingtong Yu, Zhenghao Liu, Yuan Fang, Zemin Liu, Sihong Chen, Xinming Zhang Abstract: Graph neural networks have emerged as a powerful tool for graph representation learning, but their performance heavily relies on abundant task-specific supervision. To reduce labeling requirement, the "
research-papers
Original Paper: https://arxiv.org/abs/2312.05038 By: Zilong Li, Yiming Lei, Chenglong Ma, Junping Zhang, Hongming Shan Abstract: Image restoration, which aims to retrieve and enhance degraded images, is fundamental across a wide range of applications. While conventional deep learning approaches have notably improved the image quality across
research-papers
Original Paper: https://arxiv.org/abs/2310.00085 By: Haechan Mark Bong, Rongge Zhang, Ricardo de Azambuja, Giovanni Beltrame Abstract: From industrial to space robotics, safe landing is an essential component for flight operations. With the growing interest in artificial intelligence, we direct our attention to learning based safe landing
research-papers
Original Paper: https://arxiv.org/abs/2309.02833 By: In-Ug Yoon, Tae-Min Choi, Sun-Kyung Lee, Young-Min Kim, Jong-Hwan Kim Abstract: While many FSCIL studies have been undertaken, achieving satisfactory performance, especially during incremental sessions, has remained challenging. One prominent challenge is that the encoder, trained with an ample base session
research-papers
Original Paper: https://arxiv.org/abs/2310.16427 By: Xinyuan Wang, Chenxi Li, Zhen Wang, Fan Bai, Haotian Luo, Jiayou Zhang, Nebojsa Jojic, Eric P. Xing, Zhiting Hu Abstract: Highly effective, task-specific prompts are often heavily engineered by experts to integrate detailed instructions and domain insights based on a deep