paper-with-me

홈 › Papers

BadSAM: Exploring Security Vulnerabilities of SAM via Backdoor Attacks

2023-05-05 · Zihan Guan, Mengxuan Hu, Zhongliang Zhou, Jielu Zhang, Sheng Li, Ninghao Liu

Recently, the Segment Anything Model (SAM) has gained significant attention as an image segmentation foundation model due to its strong performance on various downstream tasks. However, it has been found that SAM does not always perform satisfactorily when faced with challenging downstream tasks. This has led downstream users to demand a customized SAM model that can be adapted to these downstream tasks. In this paper, we present BadSAM, the first backdoor attack on the image segmentation foundation model. Our preliminary experiments on the CAMO dataset demonstrate the effectiveness of BadSAM.

📄 PDF Abstract BibTeX arXiv:2305.03289

Code (0)

등록된 구현이 없습니다.

Tasks

Backdoor AttackImage SegmentationSegmentationSemantic Segmentation

Methods 이 논문이 사용한 방법론

SAM 설명 없음

Similar Papers 제목 키워드 기반

Exploring Vulnerabilities and Protections in Large Language Models: A Survey

2024-06-01 · Frank Weizhen Liu, Chenhui Hu

As Large Language Models (LLMs) increasingly become key components in various AI applications, understanding their security vulnerabilities and the effectiveness of defense mechanisms is crucial. This survey examines the…

Data PoisoningSurvey

A Survey of Recent Backdoor Attacks and Defenses in Large Language Models

2024-06-10 · Shuai Zhao, Meihuizi Jia, Zhongliang Guo, Leilei Gan 외

Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot setti…

parameter-efficient fine-tuning

BadGPT: Exploring Security Vulnerabilities of ChatGPT via Backdoor Attacks to InstructGPT

2023-02-21 · Jiawen Shi, Yixin Liu, Pan Zhou, Lichao Sun

Recently, ChatGPT has gained significant attention in research due to its ability to interact with humans effectively. The core idea behind this model is reinforcement learning (RL) fine-tuning, a new paradigm that allow…

Backdoor AttackLanguage ModelingLanguage Modellingreinforcement-learning+1

Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-based Decision-Making Systems

2024-05-27 · Ruochen Jiao, Shaoyuan Xie, Justin Yue, Takami Sato 외

Large Language Models (LLMs) have shown significant promise in real-world decision-making tasks for embodied artificial intelligence, especially when fine-tuned to leverage their inherent common sense and reasoning abili…

Autonomous DrivingCommon Sense ReasoningDecision MakingLanguage Modelling+2

Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace

2024-10-17 · Jinluan Yang, Anke Tang, Didi Zhu, Zhengyu Chen 외

Model merging has gained significant attention as a cost-effective approach to integrate multiple single-task fine-tuned models into a unified one that can perform well on multiple tasks. However, existing model merging …

Meta-Learning