DeepKeep Ltd.

BS"D

DeepKeep, a startup among the recent winners of EIC Accelerator, develops algorithmic security and algorithmic trustworthiness solutions for AI systems.

Primarily addressing LLMs and image analysis models we aim to provide:

1. Algorithmic risk assessment of AI systems (e.g. is the model vulnerable to evasion/jailbreak attacks that force it provide illegal/harmful information? are there any trustworthiness issues ? is the model unfair? does the LLM leak sensitive private data? etc.)

2. AI firewall solution (e.g. additional real-time layer that enhances algorithmic security and trustworthiness) including detection and mitigation of evasion/jailbreak attacks, handling data leakage etc.

3. AI regulation compliance evaluation/enhancement

These solutions handle multiple issues including:

1. AI systems performance Evaluation

2. Sensitive data leakage prevention

3. Hallucination handling

4. LLM guardrails (securing alignment of the LLM to certain topics),

5. Prevention of malicious jailbreak/prompt injection attacks.

6. Image data augmentation using GenAI

7. Vision systems’ failure modes analysis and weak spot detection

8. Evasion attacks on vision systems

9. Fairness and Bias issues And more