Vitaly Shmatikov
- Papers
- 8
Cite
Notes
Only stored in your browser.
8papers
Authored papers
8Learning to Detect Language Model Training Data via Active Reconstruction
arXiv 2026
Harnessing the Universal Geometry of Embeddings
arXiv 2025
Universal Zero-shot Embedding Inversion
arXiv 2025
Extracting Prompts by Inverting LLM Outputs
arXiv 2024
Language Model Inversion
arXiv 2023
Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs
arXiv 2023
Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasures
arXiv 2021
Differential Privacy Has Disparate Impact on Model Accuracy
differential-privacy-has-disparate-impact-on-1
Affiliations
No known affiliations.
Frequent co-authors
10from 8 papers