Hugging Face's logo
pascalmusabyimana's picture
1 90 231

pascalmusabyimana

pascal-maker
21world's profile picture DualityAI-RebekahBogdanoff's profile picture ltim's profile picture
Β·
https://pascal-maker.github.io/developedbypascalmusabyimana/

AI & ML interests

computer vision, nlp , machine learning and deeplearning

Recent Activity

reacted to MikeDoes's post with πŸ‘€ about 5 hours ago
What if an AI agent could be tricked into stealing your data, just by reading a tool's description? A new paper reports it's possible. The "Attractive Metadata Attack" paper details this stealthy new threat. To measure the real-world impact of their attack, the researchers needed a source of sensitive data for the agent to leak. We're proud that the AI4Privacy corpus was used to create the synthetic user profiles containing standardized PII for their experiments. This is a perfect win-win. Our open-source data helped researchers Kanghua Mo, ιΎ™ζ˜±δΈž, Zhihao Li from Guangzhou University and The Hong Kong Polytechnic University to not just demonstrate a new attack, but also quantify its potential for harm. This data-driven evidence is what pushes the community to build better, execution-level defenses for AI agents. πŸ”— Check out their paper to see how easily an agent's trust in tool metadata could be exploited: https://arxiv.org/pdf/2508.02110 #OpenSource #DataPrivacy #LLM #Anonymization #AIsecurity #HuggingFace #Ai4Privacy #Worldslargestopensourceprivacymaskingdataset
reacted to MikeDoes's post with πŸ‘€ about 5 hours ago
What if an AI agent could be tricked into stealing your data, just by reading a tool's description? A new paper reports it's possible. The "Attractive Metadata Attack" paper details this stealthy new threat. To measure the real-world impact of their attack, the researchers needed a source of sensitive data for the agent to leak. We're proud that the AI4Privacy corpus was used to create the synthetic user profiles containing standardized PII for their experiments. This is a perfect win-win. Our open-source data helped researchers Kanghua Mo, ιΎ™ζ˜±δΈž, Zhihao Li from Guangzhou University and The Hong Kong Polytechnic University to not just demonstrate a new attack, but also quantify its potential for harm. This data-driven evidence is what pushes the community to build better, execution-level defenses for AI agents. πŸ”— Check out their paper to see how easily an agent's trust in tool metadata could be exploited: https://arxiv.org/pdf/2508.02110 #OpenSource #DataPrivacy #LLM #Anonymization #AIsecurity #HuggingFace #Ai4Privacy #Worldslargestopensourceprivacymaskingdataset
liked a model 4 days ago
mlx-community/Olmo-3.1-32B-Instruct-bf16
View all activity

Organizations

MLX Community's profile picture Bitsandbytes Community's profile picture