Category: 3-SometimeTechTalk

In this episode of The BlueHat Podcast, host Nic Fillingham and Wendy Zenone share Ram Shankar Siva Kumar’s dynamic keynote from BlueHat India 2025, where he explores the evolving threat landscape of AI through the lens of the Microsoft AI Red Team. From adversarial machine learning to psychosocial harms and persuasive AI, Ram highlights real-world case studies, including prompt injection, content safety violations, and memory poisoning in AI agents. Ram underscores the urgent need for robust red teaming practices to secure AI systems against traditional security flaws and emerging threats across images, text, audio, and autonomous agents. 

In This Episode You Will Learn:  

• Why old-school security flaws still break modern AI systems 
• Real-world AI red teaming in action, from scams to memory hacks 
• How small input tweaks can fool AI across images, audio, and text 

Some Questions We Ask: 

• Can attackers fool AI using just slight image changes? 
• Are generative AI systems vulnerable to prompt manipulation? 
• Do you need to be an expert to break an AI model? 

Resources:      

View Ram Shankar Siva Kumar on LinkedIn    

View Wendy Zenone on LinkedIn   

View Nic Fillingham on LinkedIn  

Watch Ram’s BlueHat India 2025 Keynote: BlueHat India 2025 Day 2 Keynote - Ram Shankar Siva Kumar 

Listen to Ram’s Previous Appearance on The BlueHat Podcast: Not with a Bug but with a Sticker 

Related Microsoft Podcasts:   

• Microsoft Threat Intelligence Podcast   
• Afternoon Cyber Tea with Ann Johnson   
• Uncovering Hidden Risks   

Discover and follow other Microsoft podcasts at microsoft.com/podcasts   

Hosted on Acast. See acast.com/privacy for more information.

Rob Duffy lives in New York with his family. He moved to the states to go work for a small online bookstore that we know today as Amazon. He's married with 2 kids, and enjoys to cook. But, his main passion is flying, as he has is pilots license and enjoys flying small planes. He recalls training on a simulator with a rendering of the Seattle space needle, which he got to fly next to in the real world once he got his license. He admits his wife has a love/hate relationship with his flying - IE she prefers when the flight is over.

Rob's has a track record of successfully building platforms - IE figuring out how to do things once instead of multiple times. His current company was growing through acquisitions, and Rob was brought on to unify these and create a converged platform for what the company had to offer.

This is Rob's creation story at HealthEdge.

Sponsors

• Paddle.com
• Sema Software
• PropelAuth
• Postman
• Meilisearch

Links

• https://healthedge.com/
• https://www.linkedin.com/in/platformduffy/

proxyfeed-jUAqjtCx

Gemini 2.5 is DeepMind’s most advanced model yet, with strong reasoning and coding capabilities. 

Connect with Tulsee on LinkedIn.

Connect with Logan on LinkedIn and Stack Overflow. 

Check out our previous episode with Logan, we discussed his unique path from coding to AI to product, the challenges of non-determinism in AI models, and surprising lessons from working at the Apple Store.

Congrats to Populous badge winner Pascal MARTIN for answering the question PHP echo vs PHP short echo tags.

Alex Kantrowitz joins live from WWDC, where Apple just announced a number of new design changes including a completely updated operating system with 'Liquid Glass' styling. But in an era of reinvention, where AI is at the center of the technology's evolution, Apple introduced a number of refinements. This short, solo episode looks at Apple's strategy, vision, and execution in a changing moment for the tech industry.

---

Enjoying Big Technology Podcast? Please rate us five stars ⭐⭐⭐⭐⭐ in your podcast app of choice.

Want a discount for Big Technology on Substack? Here’s 25% off for the first year: https://www.bigtechnology.com/subscribe?coupon=0843016b

Questions? Feedback? Write to: bigtechnologypodcast@gmail.com

• platformdirs
• poethepoet - “Poe the Poet is a batteries included task runner that works well with poetry or with uv.”
• Python Pandas Ditches NumPy for Speedier PyArrow
• pointblank: Data validation made beautiful and powerful
• Extras
• Joke

About the show

Sponsored by us! Support our work through:

• Our courses at Talk Python Training
• The Complete pytest Course
• Patreon Supporters

Connect with the hosts

• Michael: @mkennedy@fosstodon.org / @mkennedy.codes (bsky)
• Brian: @brianokken@fosstodon.org / @brianokken.bsky.social
• Show: @pythonbytes@fosstodon.org / @pythonbytes.fm (bsky)

Join us on YouTube at pythonbytes.fm/live to be part of the audience. Usually Monday at 10am PT. Older video versions available there too.

Finally, if you want an artisanal, hand-crafted digest of every week of the show notes in email form? Add your name and email to our friends of the show list, we'll never share it.

Michael #1: platformdirs

• A small Python module for determining appropriate platform-specific dirs, e.g. a "user data dir".
• Why the community moved on from appdirs to platformdirs
• At AppDirs:
  • Note: This project has been officially deprecated. You may want to check out pypi.org/project/platformdirs/ which is a more active fork of appdirs. Thanks to everyone who has used appdirs. Shout out to ActiveState for the time they gave their employees to work on this over the years.
• Better than AppDirs:
  • Works today, works tomorrow – new Python releases sometimes change low-level APIs (win32com, pathlib, Apple sandbox rules). platformdirs tracks those changes so your code keeps running.
  • First-class typing – no more types-appdirs stubs; editors autocomplete paths as Path objects.
  • Richer directory set – if you need a user’s Downloads folder or a per-session runtime dir, there’s a helper for it.
  • Cleaner internals – rewritten to use pathlib, caching, and extensive test coverage; all platforms are exercised in CI.
  • Community stewardship – the project lives in the PyPA orbit and gets security/compatibility patches quickly.

Brian #2: poethepoet - “Poe the Poet is a batteries included task runner that works well with poetry or with uv.”

• from Bob Belderbos
• Tasks are easy to define and are defined in pyproject.toml

Michael #3: Python Pandas Ditches NumPy for Speedier PyArrow

• Pandas 3.0 will significantly boost performance by replacing NumPy with PyArrow as its default engine, enabling faster loading and reading of columnar data.
• Recently talked with Reuven Lerner about this on Talk Python too.
• In the next version, v3.0, PyArrow will be a required dependency, with pyarrow.string being the default type inferred for string data.
• PyArrow is 10 times faster.
• PyArrow offers columnar storage, which eliminates all that computational back and forth that comes with NumPy.
• PyArrow paves the way for running Pandas, by default, on Copy on Write mode, which improves memory and performance usage.

Brian #4: pointblank: Data validation made beautiful and powerful

• “With its … chainable API, you can … validate your data against comprehensive quality checks …”

Extras

Brian:

• Ruff rules
• Ruff users, what rules are using and what are you ignoring?
• Python 3.14.0b2 - did we already cover this?
• Transferring your Mastodon account to another server, in case anyone was thinking about doing that
• I’m trying out Fathom Analytics for privacy friendly analytics

Michael:

• Polars for Power Users: Transform Your Data Analysis Game Course

Joke: Does your dog bite?

Ranjan Roy from Margins is back for our weekly discussion of the latest tech news. We cover: 1) What's coming at Apple's WWDC developer conference 2) Apple may be taking an AI gap year 3) Apple's Upcoming AI bets 4) Airpods enhancements 5) Apple's new operating system 6) Why Apple should buy Perplexity 7) Is Perplexity positioning itself for a sale 8) Elon vs. Trump explodes 9) What the fight means for Tesla, SpaceX, the Tech Right, and Musk's legacy 10) Why Elon needs robotaxis more than ever 11) Problems at DOGE 11) OpenAI forced to preserve our chats to due New York Times lawsuit.

---

Enjoying Big Technology Podcast? Please rate us five stars ⭐⭐⭐⭐⭐ in your podcast app of choice.

Want a discount for Big Technology on Substack? Here’s 25% off for the first year: https://www.bigtechnology.com/subscribe?coupon=0843016b

Questions? Feedback? Write to: bigtechnologypodcast@gmail.com

Emmanuel Straschnov grew up in rural France, which is interestingly enough where he started doing computer stuff (he mentioned there wasn't much else to do in the 90's). He grew up sailing, as he lived next to the shore in Normandy. He never really thought he would end up coding, but after obtaining his MBA, he ended up doing just that. Outside of tech, he is married with 2 children. He mentions that most of his hobby time is devoted to them, but on occasion, he likes to travel, continue sailing, and to sing.

Many years ago, Emmanuel noticed that there were a lot of people searching for technical founders, and using services to find technical founders. He thought this to be wrong, as many people have product ideas and just need a product to help them build it... so, he created something just for them.

This is the creation story of Bubble.

Sponsors

• Paddle.com
• Sema Software
• PropelAuth
• Postman
• Meilisearch

Links

• https://bubble.io/
• https://www.linkedin.com/in/straschnov/

Explore how Capital One is using tech to innovate the banking experience here.

Connect with Kathleen on LinkedIn and visit her blog. 

Shoutout to user Theraot for answering the questions How to connect a signal with extra arguments in Godot 4, which won them a Lifeboat badge.