DFlash: Block Diffusion for Flash Speculative Decoding
Paper ā¢ 2602.06036 ā¢ Published ā¢ 74
Gibran Iqbal
Jibbscript
AI & ML interests
None yet
Recent Activity
upvoted a paper about 1 hour ago
DFlash: Block Diffusion for Flash Speculative Decoding liked a model about 1 hour ago
z-lab/gemma-4-31B-it-DFlash liked a dataset about 1 hour ago
jamiequint/sf_criminal_courtOrganizations
upvoted a paper about 1 hour ago
liked a
model about 1 hour ago
liked a
dataset about 1 hour ago
upvoted a paper about 10 hours ago
liked a
model 2 days ago
upvoted a collection 3 days ago
liked a
dataset 5 days ago
liked 2
models 5 days ago
upvoted 2
papers 6 days ago
reacted to MikeDoes's post with š 7 days ago
Post
2041
š”ļø At Ai4Privacy, our goal is to empower researchers to build a safer AI ecosystem. Today, we're highlighting crucial research that does just that by exposing a new vulnerability.
The paper "Forget to Flourish" details a new model poisoning technique. It's a reminder that as we fine-tune LLMs, our anonymization and privacy strategies must evolve to counter increasingly sophisticated threats.
We're proud that the Ai4Privacy dataset was instrumental in this study. It served two key purposes:
Provided a Realistic Testbed: It gave the researchers access to a diverse set of synthetic and realistic PII samples in a safe, controlled environment.
Enabled Impactful Benchmarking: It allowed them to measure the actual effectiveness of their data extraction attack, proving it could compromise specific, high-value information.
This work reinforces our belief that progress in AI security is a community effort. By providing robust tools for benchmarking, we can collectively identify weaknesses and build stronger, more resilient systems. A huge congratulations to the authors on this important contribution.
š Read the full paper: https://arxiv.org/html/2408.17354v1
#OpenSource #DataPrivacy #LLM #Anonymization #AIsecurity #HuggingFace #Ai4Privacy #World's largest open privacy masking dataset
The paper "Forget to Flourish" details a new model poisoning technique. It's a reminder that as we fine-tune LLMs, our anonymization and privacy strategies must evolve to counter increasingly sophisticated threats.
We're proud that the Ai4Privacy dataset was instrumental in this study. It served two key purposes:
Provided a Realistic Testbed: It gave the researchers access to a diverse set of synthetic and realistic PII samples in a safe, controlled environment.
Enabled Impactful Benchmarking: It allowed them to measure the actual effectiveness of their data extraction attack, proving it could compromise specific, high-value information.
This work reinforces our belief that progress in AI security is a community effort. By providing robust tools for benchmarking, we can collectively identify weaknesses and build stronger, more resilient systems. A huge congratulations to the authors on this important contribution.
š Read the full paper: https://arxiv.org/html/2408.17354v1
#OpenSource #DataPrivacy #LLM #Anonymization #AIsecurity #HuggingFace #Ai4Privacy #World's largest open privacy masking dataset
liked 2
datasets 8 days ago
liked 2
models 9 days ago
upvoted a paper 9 days ago
liked 3
models 9 days ago