Lessons from Defending Gemini Against Indirect Prompt Injections
Paper
•
2505.14534
•
Published
•
8
Chawin Sitawarin
chawins
AI & ML interests
None yet
Recent Activity
liked
a model
2 months ago
JoyYizhu/DataFilter
liked
a model
6 months ago
facebook/Meta-SecAlign-8B
liked
a dataset
6 months ago
microsoft/llmail-inject-challenge
Organizations
authored
a
paper
7 months ago
authored
6
papers
over 1 year ago
StruQ: Defending Against Prompt Injection with Structured Queries
Paper
•
2402.06363
•
Published
•
2
Mark My Words: Analyzing and Evaluating Language Model Watermarks
Paper
•
2312.00273
•
Published
•
3
Jatmo: Prompt Injection Defense by Task-Specific Finetuning
Paper
•
2312.17673
•
Published
•
1
SPDER: Semiperiodic Damping-Enabled Object Representation
Paper
•
2306.15242
•
Published
PubDef: Defending Against Transfer Attacks From Public Models
Paper
•
2310.17645
•
Published
REAP: A Large-Scale Realistic Adversarial Patch Benchmark
Paper
•
2212.05680
•
Published