104
Addit
⚡
Add objects to images using text prompts
vikas patel
vikaswebdev
AI & ML interests
None yet
Recent Activity
liked
a Space
6 days ago
nvidia/addit
liked
a dataset
6 days ago
NousResearch/Hermes-3-Dataset
liked
a model
7 days ago
MiniMaxAI/MiniMax-M1-80k
Organizations
None yet
liked
a
Space
6 days ago
liked
a
dataset
6 days ago
liked
a
model
7 days ago
liked
2
models
8 days ago
liked
a
Space
8 days ago
liked
a
model
9 days ago
liked
a
model
16 days ago
liked
a
model
27 days ago
liked
2
Spaces
about 1 month ago
liked
a
model
about 1 month ago
liked
a
model
about 2 months ago
reacted to
DualityAI-RebekahBogdanoff's
post with ❤️
about 2 months ago
Post
2078
🗣️ 📢 New article alert!
"Integrity Threats in AI: When Data Poisoning Undermines Model Effectiveness" from Duality AI is now on HuggingFace here: https://huggingface.co/blog/DualityAI-RebekahBogdanoff/integrity-threats-in-ai
Significant threats to AI model performance aren’t always loud or obvious. Integrity violations—like subtle data poisoning attacks—can quietly erode your model’s reliability, long before anyone notices. These attacks can be surprisingly effective with minimal changes to the dataset.
At Duality, our work in high-stakes sectors like defense has driven us to tackle this threat head-on. In our latest blog from Duality's Director of Infrastructure and Security at Duality, David Strout, we unpack how data poisoning works, why it’s so dangerous, and how organizations can secure their AI pipelines with clear provenance, regular performance auditing, and a trusted synthetic data supply chain.
Whether you're building AI models for finance, healthcare, manufacturing, or national security—the integrity of these systems is a matter of public safety and security. Taking action today will mitigate fundamental business risks in the very near tomorrow.
"Integrity Threats in AI: When Data Poisoning Undermines Model Effectiveness" from Duality AI is now on HuggingFace here: https://huggingface.co/blog/DualityAI-RebekahBogdanoff/integrity-threats-in-ai
Significant threats to AI model performance aren’t always loud or obvious. Integrity violations—like subtle data poisoning attacks—can quietly erode your model’s reliability, long before anyone notices. These attacks can be surprisingly effective with minimal changes to the dataset.
At Duality, our work in high-stakes sectors like defense has driven us to tackle this threat head-on. In our latest blog from Duality's Director of Infrastructure and Security at Duality, David Strout, we unpack how data poisoning works, why it’s so dangerous, and how organizations can secure their AI pipelines with clear provenance, regular performance auditing, and a trusted synthetic data supply chain.
Whether you're building AI models for finance, healthcare, manufacturing, or national security—the integrity of these systems is a matter of public safety and security. Taking action today will mitigate fundamental business risks in the very near tomorrow.
liked
a
Space
about 2 months ago
liked
2
models
about 2 months ago
liked
a
model
2 months ago
liked
a
dataset
2 months ago
liked
a
model
2 months ago
