x

75% of people globally want unbiased news (Pew Research) but are concerned they're not getting that.

Get balanced coverage with Symby. See how stories are covered across diverse outlets and spot when one side covers a story the other skips.

PODCAST

Certified - Responsible AI Audio Course

The **Responsible AI Audio Course** is a 50-episode learning series that explores how artificial intelligence can be designed, governed, and deployed responsibly. Each narrated episode breaks down complex technical, ethical, legal, and organizational issues into clear, accessible explanations built for audio-first learning—no visuals required. You’ll gain a deep understanding of fairness, transparency, safety, accountability, and governance frameworks, along with practical guidance on implementing

education courses

All Episodes

23:42

Episode 31 — Red Teaming & Safety Evaluations

Certified - Responsible AI Audio Course ·

2025/09/15

Red teaming and safety evaluations are proactive practices designed to uncover vulnerabilities and harms in AI systems before they reach users. This episode defines red teaming as structured adversarial testing, where internal or external groups simulate attacks and misuse. Safety evaluations are broader reviews assessing robustness, fairness, reliability, and harmful outputs. Together, these practices ensure AI systems are not only technically functional but also resilient to exploitation

en

25:06

Episode 30 — Content Safety & Toxicity

Certified - Responsible AI Audio Course ·

2025/09/15

AI systems that generate or moderate content must address the risk of harmful outputs. This episode introduces content safety as a set of controls designed to prevent the creation or spread of offensive, abusive, or dangerous material. Toxicity is defined as harmful language, including hate speech, harassment, and discriminatory content. Learners explore the technical role of classifiers, thresholds, and moderation pipelines, and how escalation protocols integrate human oversight when

en

24:52

Episode 29 — LLM Specific Risks

Certified - Responsible AI Audio Course ·

2025/09/15

Large language models (LLMs) present risks distinct from earlier AI systems due to their general-purpose scope and broad deployment. This episode highlights unique threats such as prompt injection, where malicious instructions override safeguards; jailbreaks, where restrictions are bypassed; data leakage, where models expose sensitive training data; and hallucinations, where false but plausible outputs undermine trust. Learners also explore risks tied to model scale, including economic

en

23:27

Episode 28 — Adversarial ML

Certified - Responsible AI Audio Course ·

2025/09/15

Adversarial machine learning focuses on how attackers manipulate AI models and how defenders respond. This episode introduces four major categories of adversarial attacks: evasion, where crafted inputs mislead models; poisoning, where malicious data corrupts training; extraction, where repeated queries replicate models; and inference, where attackers uncover sensitive training data. Learners gain an overview of why AI is uniquely vulnerable, especially in high-dimensional models such as

en

25:28

Episode 27 — Threat Modeling for AI Systems

Certified - Responsible AI Audio Course ·

2025/09/15

Threat modeling is the process of systematically identifying and prioritizing risks that could compromise AI systems. This episode introduces the core components of threat modeling: defining assets, identifying adversaries, mapping attack surfaces, and assessing likelihood and impact. Learners see how existing frameworks like STRIDE (spoofing, tampering, repudiation, information disclosure, denial of service, elevation of privilege) can be adapted to AI contexts, particularly given

en

25:10

Episode 26 — Retention, Deletion & Data Rights

Certified - Responsible AI Audio Course ·

2025/09/15

Responsible AI requires clear practices for how long data is kept, how it is securely deleted, and how organizations honor user rights. This episode defines retention as the rules that govern storage duration, deletion as the process of secure removal across live systems and backups, and rights as the legal and ethical obligations to provide users with access, correction, portability, and erasure of their information. Learners see how these practices align with regulations such as the

en

20:13

Episode 25 — Synthetic Data

Certified - Responsible AI Audio Course ·

2025/09/15

Synthetic data is artificially generated to mimic real datasets while reducing reliance on sensitive information. This episode explains how it can protect privacy, expand small datasets, and create scenarios for testing. Learners explore generation techniques including statistical sampling, generative adversarial networks (GANs), and simulation models. Synthetic data is framed as both an opportunity to reduce risks and a tool for fairness by improving representation of underrepresented

en

20:10

Episode 24 — Federated & Edge Approaches

Certified - Responsible AI Audio Course ·

2025/09/15

Federated learning and edge AI represent architectural strategies to protect privacy and reduce reliance on centralized data collection. Federated learning trains models across multiple devices or servers without centralizing raw data, while edge AI processes data locally on devices. This episode introduces both approaches and explains how they reduce risks by limiting data movement, while also providing performance advantages such as reduced latency and greater resilience to connectivity

en

19:44

Episode 23 — Differential Privacy in Practice

Certified - Responsible AI Audio Course ·

2025/09/15

Differential privacy provides mathematical guarantees that individual records cannot be re-identified from aggregated results. This episode introduces its core concept: adding controlled noise to outputs so the inclusion or exclusion of one person’s data does not significantly change results. Learners explore the privacy budget, often described through the epsilon parameter, and how smaller values mean stronger protection but reduced accuracy. Differential privacy is positioned as a modern

en

19:27

Episode 22 — Privacy by Design for AI

Certified - Responsible AI Audio Course ·

2025/09/15

Privacy by design is the principle of embedding privacy protections into systems from the outset rather than adding them later. This episode introduces its core principles, including proactive safeguards, privacy as the default setting, and end-to-end lifecycle protection. Learners explore how privacy by design ensures compliance with regulations such as the General Data Protection Regulation (GDPR) and supports trust with users. Key practices include minimizing the amount of data

en

20:36

Episode 21 — Communicating with Humans

Certified - Responsible AI Audio Course ·

2025/09/15

Responsible AI requires not just transparency in technical systems but also clear communication that humans can understand and trust. This episode explains the principles of user-centered communication, including tailoring explanations for different audiences such as regulators, executives, and end-users. Progressive disclosure is introduced as a method for layering information, providing high-level clarity first and more detailed technical explanations when appropriate. Learners understand

en

20:16

Episode 20 — Model, Data & System Cards

Certified - Responsible AI Audio Course ·

2025/09/15

en

21:33

Episode 19 — Explainer Tooling

Certified - Responsible AI Audio Course ·

2025/09/15

Explainer tools operationalize post hoc explainability by generating insights into model behavior. This episode introduces SHAP, which uses game theory to allocate feature importance, LIME, which builds simple local approximations, and integrated gradients, which identify contributions of features in neural networks. Learners understand the strengths, limitations, and appropriate use cases for each tool. These methods allow organizations to detect bias, debug models, and provide

en

21:27

Episode 18 — Interpretable Models vs. Post hoc...

Certified - Responsible AI Audio Course ·

2025/09/15

This episode contrasts two approaches to explainability: inherently interpretable models and post hoc explanation methods. Interpretable models, such as decision trees and logistic regression, are inherently transparent but may struggle with complex tasks. Post hoc explanations, such as SHAP and LIME, provide insights into more opaque models like deep neural networks. Learners gain clarity on the trade-offs between simplicity and performance, and on when each approach is appropriate.Case

en

21:27

Episode 17 — Why Explainability?

Certified - Responsible AI Audio Course ·

2025/09/15

Explainability refers to making AI outputs understandable to humans, a necessity for trust, compliance, and accountability. This episode explains why explainability is distinct from accuracy: a model may perform well statistically yet still fail if users cannot understand its reasoning. The discussion highlights regulatory drivers such as rights to explanation in data protection laws, ethical imperatives around transparency, and practical needs for debugging and bias detection. Without

en

16:01

Episode 16 — Mitigating Bias

Certified - Responsible AI Audio Course ·

2025/09/15

Measuring bias is only the first step; mitigation strategies are required to reduce unfair outcomes in AI systems. This episode introduces three broad categories of bias mitigation: pre-processing, in-processing, and post-processing. Pre-processing techniques focus on balancing datasets through re-sampling, re-weighting, or augmentation. In-processing integrates fairness constraints directly into algorithms, including adversarial debiasing and regularization methods. Post-processing adjusts

en

20:44

Episode 15 — Measuring Bias

Certified - Responsible AI Audio Course ·

2025/09/15

Once fairness definitions are understood, the next step is measuring bias within data and models. This episode explains how metrics quantify disparities across groups, using measures such as false positive rate differences, demographic parity gaps, and calibration error. Learners also explore approaches to detecting proxy variables, where seemingly neutral features act as stand-ins for sensitive attributes. Effective bias measurement requires selecting metrics appropriate to the domain,

en

21:48

Episode 14 — Fairness Definitions

Certified - Responsible AI Audio Course ·

2025/09/15

Fairness in AI does not have a single definition but instead encompasses multiple, sometimes conflicting, interpretations. This episode introduces demographic parity, which requires equal outcomes across groups, equal opportunity, which ensures equal true positive rates, and equalized odds, which balances both true and false positive rates across populations. Calibration and individual fairness, which require reliable probabilities and consistent treatment of similar individuals, are also

en

23:03

Episode 13 — Documenting Data

Certified - Responsible AI Audio Course ·

2025/09/15

Documenting datasets is critical for transparency, accountability, and reproducibility in AI systems. This episode introduces methods such as datasheets for datasets, data statements, and factsheets, all of which capture key details about origins, intended use, limitations, and risks. Documentation ensures that future users understand the context of a dataset and prevents misuse, particularly when training data contains sensitive or potentially biased information. By making assumptions and

en

22:22

Episode 12 — Data Governance 101

Certified - Responsible AI Audio Course ·

2025/09/15

Data governance establishes the rules and responsibilities for managing the information that powers AI systems. This episode defines data governance as encompassing quality, lineage, ownership, and security. Without strong governance, models risk producing unreliable, biased, or unsafe outputs. Learners explore how governance frameworks align with privacy requirements, ethical obligations, and compliance standards. Clear ownership ensures accountability for datasets, lineage tracks sources

en

51 results

Similar Podcasts

Science Talk

Albert Einstein College of Medicine

五分钟心理学

柠檬心理

Daily Facts

Amalia Dupray and Montgomery Jones.

Les dents et dodo

BFMTV

Veterinary Clinical Podcasts

The Royal Veterinary College