Menu
  • AI Governance Overview
  • 358 pages and 90 vendors
  • 90 controls and 25 case studies
  • Mappings to EU AI Act and NIST AI RMF
Download Book
Vertical Line
  • Agentic AI Governance
  • 19 case studies
  • 11 Agentic AI platforms
  • Companion to AI Governance Comprehensive
Download Book

Using Amazon Bedrock AI Guardrails with DeepSeek to Block Problematic Content

Sunil Soares, Founder & CEO, YDC February 17, 2025
In a previous blog, I discussed AI Governance challenges associated with DeepSeek, especially China data risks. Several vendors like Amazon Web Services (AWS), Perplexity, and Microsoft Azure are embedding DeepSeek within their offerings to mitigate some of these risks.

As shown in the blog, DeepSeek already blocks toxic prompts with native AI Guardrails. In this blog, we discuss the use of Amazon Bedrock AI Guardrails with DeepSeek to block additional problematic content such as Competitor Mentions and Off-Topic prompts.

Used DeepSeek-R1-Distill-Qwen-7B Model within Amazon Bedrock

We used the DeepSeek-R1-Distill-Qwen-7B model within Amazon Bedrock.

Using Amazon Bedrock, we were able to generate successful responses from DeepSeek to a prompt requesting vegetarian options for McDonald’s.


Creating AI Guardrail to Block Competitor Mentions

AWS offers support for the  Amazon Bedrock ApplyGuardrail API to create custom AI Guardrails such as blocking prompts that contain competitor mentions or that are off-topic. We added a Block Competitor Information Guardrail in Bedrock to avoid responses relating to McDonald’s competitors.


For added protection, we also added Word Filters in Bedrock.

As a result, a prompt requesting information about Domino’s was blocked in Bedrock.


A prompt containing Burger King was also blocked.


Creating AI Guardrail to Block Off-Topic Prompts

We created AI guardrails to block off-topic prompts.


The image below shows the details of the Off-Topic Guardrail. We created multiple Off-Topic Guardrails due to the limit of 200 characters in Bedrock.
As a result, Bedrock blocked an off-topic prompt relating to the U.S. President.

Recent Posts

10268 SW Visconti Way

Port St. Lucie, FL 34986

X-twitter Linkedin
Copyright 2025 YDC™ is a registered trademark of YourDataConnect, LLC. All Rights Reserved.

Fairness & Accessibility

Component

Component ID: 5.0

Mitigate bias and manage AI accessibility.

List of Controls:

  • Bias
  • Accessibility
Mitigate Bias
Control
View Details
ID: 5.1

Ensure that AI systems are fair and manage harmful bias.
Component
Sub-Control
Regulation
  
Source
Address Fairness and Accessibility EU AI Act -Article 10(2)(f)(g) – Data and Data Governance (“Examination of Possible Biases”)

Vendors

Detect Data Poisoning Attacks
Control

View Details

ID: 10.4.1

Data poisoning involves the deliberate and malicious contamination of data to compromise the performance of AI and machine learning systems.

Component
Control
Regulation
Source
10. Improve Security10.4 Avoid Data and Model Poisoning AttacksEU AI Act: Article 15 – Accuracy, Robustness and Cybersecurity 

Vendors

Improve Security
Component

Component ID: 10

Address emerging attack vectors impacting availability, integrity, abuse, and privacy.  

List of Controls:

  • Prevent Direct Prompt Injection Including Jailbreak
  • Avoid Indirect Prompt Injection
  • Avoid Availability Poisoning
    • Manage Increased Computation Attack
    • Detect Denial of Service (DoS) Attacks
    • Prevent Energy-Latency Attacks
  • Avoid Data and Model Poisoning Attacks
    • Detect Data Poisoning Attacks
    • Avoid Targeted Poisoning Attacks
    • Avoid Backdoor Poisoning Attacks
    • Prevent Model Poisoning Attacks
  • Support Data and Model Privacy
    • Prevent Data Reconstruction Attacks
    • Prevent Membership Inference Attacks
    • Avoid Data Extraction Attacks
    • Avoid Model Extraction Attacks
    • Prevent Property Inference Attacks
    • Prevent Prompt Extraction Attacks
  • Manage Abuse Violations
    • Detect White-Box Evasion Attacks
    • Detect Black-Box Evasion Attacks
    • Mitigate Transferability of Attacks
  • Misuse of AI Agents
    • Prevent AI-Powered Spear-Phishing at Scale
    • Prevent AI-Assisted Software Vulnerability Discovery
    • Prevent Malicious Code Generation
    • Identify Harmful Content Generation at Scale
    • Detect Non-Consensual Content
    • Detect Fraudulent Services
    • Prevent Delegation of Decision-Making Authority to Malicious Actors

Identify Executive Sponsor

View Details

ID : 1.1 

Appoint an executive who will be accountable for the overall success of the program.

ComponentRegulationVendors
1. Establish Accountability for AIEU AI Act 
We use cookies to ensure we give you the best experience on our website. If you continue to use this site, we will assume you consent to our privacy policy.
OK