# privacy (video feeds) — RSS Amplifier

Recent posts from the 2 feeds in the RSS Amplifier directory that cover privacy.

Page: <https://rssamplifier.com/topics/privacy/videos>  
Feed: <https://rssamplifier.com/topics/privacy/videos.md>

---

## Pragathi Jha, Modeling Cyber Adversaries: A Critical Survey of Methods and Assumptions

_2026-04-29 · webmaster@cerias.purdue.edu (CERIAS \<webmaster@cerias.purdue.edu\>) · CERIAS Weekly Security Seminar - Purdue University_

Cybersecurity practitioners face a persistent methodological problem: how should we reason about intelligent adversaries who observe our defenses, adapt their tactics, and choose targets based on our vulnerabilities? The field has responded with a fragmented toolkit. Quantitative risk assessment borrowed from safety engineering treats threat, vulnerability, and consequence as independent terms.…

[Listen](https://www.cerias.purdue.edu/assets/video/secsem/secsem_20260429.mp4)

## Smriti Bhatt, Evolving Security Landscape in the Agentic AI-Enabled IoT Era

_2026-04-22 · webmaster@cerias.purdue.edu (CERIAS \<webmaster@cerias.purdue.edu\>) · CERIAS Weekly Security Seminar - Purdue University_

The rapid evolution of connected devices and technologies has transformed the Internet of Things (IoT) into increasingly intelligent and autonomous systems. This talk focuses on the progression from traditional IoT to the Artificial Intelligence of Things (AIoT), and further toward Agent-Based IoT (AB-IoT), also referred to as Agentic AI-enabled IoT. As intelligent agents become embedded within…

[Listen](https://www.cerias.purdue.edu/assets/video/secsem/secsem_20260422.mp4)

## Gary Hayslip, The AI Arms Race

_2026-04-15 · webmaster@cerias.purdue.edu (CERIAS \<webmaster@cerias.purdue.edu\>) · CERIAS Weekly Security Seminar - Purdue University_

Ransomware has evolved from basic digital extortion into a sophisticated, AI-powered threat that's faster,smarter, and more devastating than ever before. In this session, we'll explore how threat actors are weaponizing artificial intelligence to supercharge their operations—from automated reconnaissance and hyper-realistic phishing to malware that adapts in real-time to evade detection. We'll also…

[Listen](https://www.cerias.purdue.edu/assets/video/secsem/secsem_20260415.mp4)

## Brian Peretti, Symposium Closing Keynote: AI, Cybersecurity, and the Path Forward

_2026-04-08 · webmaster@cerias.purdue.edu (CERIAS \<webmaster@cerias.purdue.edu\>) · CERIAS Weekly Security Seminar - Purdue University_

Annual Security Symposium. Visit: https://ceri.as/2026 Artificial intelligence is rapidly transforming both the opportunities and risks within cybersecurity, creating a new landscape that today's students and researchers will soon inherit and shape. This keynote explores how AI is evolving from a supporting tool to a decision-making system, fundamentally changing how cyber threats are created,…

[Listen](https://www.cerias.purdue.edu/assets/video/secsem/secsem_20260408.mp4)

## Jen Sims, Analyzing Supply Chain Risk in Mobile Applications for Home Energy Storage Systems

_2026-04-01 · webmaster@cerias.purdue.edu (CERIAS \<webmaster@cerias.purdue.edu\>) · CERIAS Weekly Security Seminar - Purdue University_

The rapid adoption of mobile applications for managing consumer whole-house battery and energy systems has introduced new questions about software supply chain security. While these applications are not currently integrated with critical infrastructure, their growing role in connected energy environments highlights the importance of understanding the dependencies,permissions, and external services…

[Listen](https://www.cerias.purdue.edu/assets/video/secsem/secsem_20260401.mp4)

## Kelechi Kalu, Software Signing in Practice: Lessons from Adoption and Usability Toward Broader Supply Chain Trust

_2026-03-25 · webmaster@cerias.purdue.edu (CERIAS \<webmaster@cerias.purdue.edu\>) · CERIAS Weekly Security Seminar - Purdue University_

Software signing is a foundational mechanism for improving software supply-chain security because it helps establish artifact provenance, integrity, and authenticity across organizational boundaries. Yet the security value of software signing depends not only on cryptographic design, but also on whether signing is adopted, integrated, and used correctly in practice. This research examines these…

[Listen](https://www.cerias.purdue.edu/assets/video/secsem/secsem_20260311.mp4)

## Ruqi Zhang, Discovering and Controlling AI Safety Risks in Foundation Models: A Probabilistic Perspective

_2026-03-04 · webmaster@cerias.purdue.edu (CERIAS \<webmaster@cerias.purdue.edu\>) · CERIAS Weekly Security Seminar - Purdue University_

As foundation models, including large language models and multimodal models, are increasingly deployed in complex and high-stakes settings, ensuring their safety has become more important than ever. In this talk, I present a probabilistic perspective on AI safety: safety risks are treated as structured distributions to be discovered and controlled, rather than isolated failures to be patched. I…

[Listen](https://www.cerias.purdue.edu/assets/video/secsem/secsem_20260304.mp4)

## Danny Vukobratovich, ISO 27001 as the Engine, NIST CSF 2.0 as the Dashboard, A Practical Operating Model

_2026-02-25 · webmaster@cerias.purdue.edu (CERIAS \<webmaster@cerias.purdue.edu\>) · CERIAS Weekly Security Seminar - Purdue University_

Many organizations adopt security frameworks but struggle to turn them into day-to-day operations that reduce risk without slowing delivery. This talk presents a practical operating model that pairs ISO/IEC 27001 (as the certifiable management system that runs governance, risk management, internal audit, and continual improvement) with NIST Cybersecurity Framework 2.0 (as the outcome-focused…

[Listen](https://www.cerias.purdue.edu/assets/video/secsem/secsem_20260225.mp4)

## Thai Le, Towards Robust and Trustworthy AI Speech Models: What You Read Isn't What You Hear

_2026-02-18 · webmaster@cerias.purdue.edu (CERIAS \<webmaster@cerias.purdue.edu\>) · CERIAS Weekly Security Seminar - Purdue University_

Deepfake voice technology is rapidly advancing, but how well do current detection systems handle differences in language and writing style? Most existing work focuses on robustness to acoustic variations such as background noise or compression, while largely overlooking how linguistic variation shapes both deepfake generation and detection. Yet language matters: psycholinguistic features such as…

[Listen](https://www.cerias.purdue.edu/assets/video/secsem/secsem_20260218.mp4)

