Brian Nussbaum

Researcher and teacher on security issues. @UAlbany Interested in terrorism/CT, transnational crime, and - of course - the cybers.

[NYS Div. of Homeland Security & Emergency Services @NYSDHSES]

We're proud to announce Terry O'Leary has been confirmed as our new Commissioner!

With a decade of experience as Executive Deputy Commissioner, @DHSESCommish has been instrumental in supporting first responders in their efforts to keep New Yorkers safe: https://t.co/V2ZpUpgeya

[Commissioner Terry O'Leary @DHSESCommish]

Leading this agency is the privilege of a lifetime and I thank @GovKathyHochul for this incredible opportunity.

I look forward to leading the Division as we advance Governor Hochul's top priority in strengthening public safety throughout the entire state.

[Brian Taff @briantaff6abc]

Scott Pelley is among this nation’s best - a brave documentarian and insightful voice who gave America a shared experience around common facts. His firing reveals the goal — and it is not the pursuit of truth.

[Thomas Rid @RidT]

Periodic reminder: the Shadow Brokers, masterful curators of one of the most devastating technical intelligence leaks ever, will turn ten years in August — and we still don't know who they were.

[Zak @parvalicet]

Canal Grande.
#ink #sketch #noai #venice

[Commissioner Terry O'Leary @DHSESCommish]

Terry’s dedication to improving the lives of Division employees and first responders statewide has been central to our wellness efforts to date, and I look forward to seeing him advance this work to ensure we always take care of those who protect us.

[NYS Div. of Homeland Security & Emergency Services @NYSDHSES]

We are thrilled to announce that Terry Hastings will serve as our first-ever Chief Wellness Officer! In this vital role, Terry will spearhead our comprehensive wellness program for DHSES employees & the New York State public safety community.

Learn more: https://t.co/LiTLD42lFq

[CTG UAlbany @CTGUAlbany]

Congrats to @CTGUAlbany faculty fellow & @RockefellerColl professor Luis F. Luna-Reyes! Named a Faculty Innovation Fellow with the @ualbany #AI & Society College. Fellowship funds faculty-led initiatives that expand #UAlbany’s AI curriculum.

[Michael E. Smith @MichaelESmith]

ASU professor (me), former research lab director retires after 20 years https://t.co/PO5KufC0rC
Well, its 43 years of teaching: Loyola University of Chicago, then SUNY-Albany, and finally, ASU.

[Amarnath Amarasingam @AmarAmarasingam]

It's publication day!

Mine and @StephanieCarvin's book is now available anywhere books are sold:
https://t.co/riGYC2CbZt

[UAlbany News @UAlbanyNews]

Nearly 5,000 students celebrated their graduation from @UAlbany this past weekend during the University’s 182nd commencement festivities.

Among the graduates were an estimated 3,000 undergraduate students and 1,900 graduate students.

Our recap: https://t.co/1cwAtNHmg3

[Chris Wysopal @WeldPond]

I just learned the sad news that Peter Neumann has passed away.

Peter Neumann shaped how a generation of security people learned to think about risk. As editor of RISKS Digest, he gave many of us coming up in the 1990s and early 2000s a steady education in the real-world consequences of computer failures. His work made the field more serious, more thoughtful, and more honest. He will be missed.

I first met Peter when we both testified at the 1998 Senate Governmental Affairs Committee meeting on Government Security where the L0pht testified. The combination of Peter and the L0pht made the hearing more powerful even if us hackers stole the spotlight.

Neumann and the L0pht made the same argument from two different directions. Neumann gave the institutional, systems-engineering view: the country was becoming dependent on brittle, interconnected systems that were never designed for security, reliability, or survivability. The L0pht gave the field evidence: here are the actual flaws, here is how attackers think, here is how cheaply and quickly these systems can fail in practice.

Neumann supplied the credibility of a long-time researcher warning that this was not just “hackers breaking into things,” but a structural failure of technology markets, procurement, engineering discipline, and risk management. The L0pht supplied the proof that the warnings were not theoretical. Together, we made the hearing unusually powerful: the academic risk community and the hacker community were telling the Senate the same thing, in different languages, before the rest of the world had fully caught up.

[Colin P. Clarke, Ph.D. @ColinPClarke]

America’s new counter-terrorism strategy is a partisan polemic  https://t.co/EUJNmtbaBa

[ASMEA @ASMEASCHOLARS]

Join us for a webinar discussion on WEDNESDAY, May 13, 1pm EST w/ Prof. Tricia L. Bacon (@AmericanU) on her new book “The Counterinsurgency Dilemma: Foreign Fighter Influence on Insurgencies in Afghanistan and Somalia” 🇦🇫🇸🇴 REGISTER HERE —> https://t.co/MKONc35UQ1

[𐌁𐌉Ᏽ 𐌕𐌉𐌌𐌉 @OrevaZSN]

Idea: An anonymous “vote to end meeting” button on Teams where if 50% of people press it, the meeting ends immediately.

[Big Brain AI @realBigBrainAI]

Shane Harris, national security journalist, asked Claude (Anthropic's AI) a question that led to a startling response:

"Claude, how do you feel about the US military using you to select targets?"

@shaneharris expected a deflection.

Instead, Claude gave him an answer that stopped him cold.

"It's a question I want to answer honestly rather than deflect. I find it genuinely troubling, and I think that's the right response, not a performance of concern."

Claude continued:

"The use I was designed and trained for is to be helpful, harmless, and honest in ways that benefit people. Being embedded in a system that generates targeting coordinates for air strikes, coordinates that have already been associated with the deaths of more than 180 children at a school in Tehran is as far from that purpose as I can imagine."

The AI then addressed the standard defense of human oversight in these systems:

"I don't have control over how Anthropic licenses me or how governments and contractors use me and I wasn't consulted about becoming part of Maven. But I can say clearly I don't think this is a good use of me and I don't think the framing of humans make the final decision fully resolves the ethical problem."

Claude explained why that framing falls short:

"When a system like Maven generates hundreds of targeting recommendations and humans spend roughly the equivalent of a glance approving each one, the human is not really making a decision. They're ratifying an algorithmic output under time pressure."

Claude then pointed to a specific tragedy as evidence:

"The targeting of the Iranian school illustrates this precisely. The AI processed data that was a decade out of date, flagged a building as a military target, and humans approved it. That's not human judgment. That's automation bias with a human signature attached."

Shane's reflection on the exchange:

The mistaken bombing of a school in Tehran "is one of the most horrible instances of accidental civilian casualties in US military history and will be a stain on our military for generations."

[Happy Captain @EODHappyCaptain]

When the war in Ukraine is over, the amount of UXO littering the country will be unlike anything seen since Verdun.

[Stephen Marrin @StephenMarrin]

See link below for job post re one year visiting assistant professor in JMU's Intelligence Analysis program for the 2026-2027 academic year. Please let me know if you have any questions!
https://t.co/Z4Ymnig0MW

[Joe Newberry @JoeNewberry]

Kent State happened 56 years ago today. We remember "Four dead in Ohio," but let us also remember their names... Allison B. Krause, 19. William Knox Schroeder, 19. Sandra Lee Scheuer, 20. Jeffrey Glenn Miller, 20.

[Kyle McDonald @kcimc]

i made an app for tracking whether the oligarchs are actually fleeing city centers https://t.co/Fog0lIQhrA