DeepKeep Safeguards AI Applications Across LLM, Vision, Spatial Sensing, Human-Machine Interaction and Multimodal Models with AI-Native Security and Trustworthiness

Project Information

DeepKeep

Grant agreement ID: 101218086

DOI

10.3030/101218086

EC signature date 3 October 2025

Start date 1 June 2025

End date 31 May 2027

Funded under

• The European Innovation Council (EIC)

Total cost

No data

EU contribution

€ 2 490 250,00

Coordinated by

DEEPKEEP LTD
Israel

CORDIS provides links to public deliverables and publications of HORIZON projects.

Links to deliverables and publications from FP7 projects, as well as links to some specific result types such as dataset and software, are dynamically retrieved from OpenAIRE .

Publications

Conference proceedings (2)

Backdoors in Conditional Diffusion: Threats to Responsible Synthetic Data Pipelines

Author(s): Raz Lapid, Almog Dubin
Published in: RDS Workshop, AAAI 2026, 2026
Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.48550/ARXIV.2507.04726

Activation Steering for Masked Diffusion Language Models

Author(s): Adi Shnaidman, Erin Feiglin, Osher Yaari, Efrat Mentel, Amit Levi, Raz Lapid
Published in: ReALM-GEN Workshop, ICLR 2026
Publisher: International Conference on Learning Representations (ICLR)
DOI: 10.48550/ARXIV.2512.24143

Peer reviewed articles (1)

BenchOverflow: Measuring Overflow in Large Language Models via Plain-Text Prompts

Author(s): Erin Feiglin, Nir Hutnik, Raz Lapid
Published in: Transactions on Machine Learning Research (TMLR), ISSN 2835-8856
Publisher: Transactions on Machine Learning Research
DOI: 10.48550/ARXIV.2601.08490