8en N@$$!

🎓 Faculty, ECE @TelAvivUni |
🎩 @BlackHatEvents Review Board |
Cybersecurity | LLM & AI AppSec

[8en N@$$! @ben_nassi]

@dangoodin001 just covered our new study on 𝗕𝗲𝘄𝗮𝗿𝗲 𝗼𝗳 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗕𝗼𝘁𝗻𝗲𝘁𝘀

Co-authored by Aya Spira, Stav Cohen, Elad Feldman, Ron Bitton, Avishai Wool, and @ben_nassi .

A joint work by @TelAvivUni @TechnionLive @Intuit

A link to the the website containing the paper: https://t.co/Lpba8Jkpdb

#promptware #agents #botnets #agentic_botnet

[Ars Technica @arstechnica]

Hackers can use 9 of the most popular AI tools to assemble massive botnets https://t.co/ljCbv2odz8

[Giovanni Apruzzese @g_apru]

The AISec '26 program is out! https://t.co/oOtk365rgG

2 keynote talks, 8 spotlight presentations, and 2 poster sessions---covering the 39 accepted papers at the intersection of AI & Security/Privacy

If you're attending CCS, or are in The Hague on Nov. 15, consider stopping by!

[8en N@$$! @ben_nassi]

@XOAviStrool שי הולצמן

[Leviathan @l3v1at4an]

Legendary Jewish comedian Jerry Seinfeld expertly trolls Pro-Palestinian protestors at his show who paid decent money to sit within speaking distance of Seinfeld, who then says he’s going to find out how much their ticket prices were & donate the amount to Israel 🤣🤣🤣

[zenitylabs @zenitysec_labs]

Zero-click prompt injection?
It's a half-click. That's @ben_nassi 's correction to his own use of the term, and on ep. 3 of In the Wild, From Dumbledore to Delayed Tool Invocation, he explains why the gap matters:

[8en N@$$! @ben_nassi]

Many thanks to @zenitysec_labs and @mbrg0 for hosting me to discuss interesting topics.

Here is the second part of the podcast

#prompt_injection #LLM #infosec #cybersecurity #promptware

[Michael Bargury @mbrg0]

part 2 of my convo w/ @ben_nassi is up on in the wild!

we talk about google's response to 'invitation is all you need', CaMeL, beyond the lethal trifecta, half-click ai exploits, BlackHat submission, what is a great talk, and the real world ai security conf

[8en N@$$! @ben_nassi]

@cognition please DM ASAP me if you want to share your findings at @BlackHatEvents Europe 26 at the Crypto Track.

[8en N@$$! @ben_nassi]

אתה כל כך צודק בתחומי מדעי המחשב!
אבל ראוי לציין שזה משתנה בין תחומים.
יש תחומים בהם המחקר הוא המוצר המוגמר (למשל במחקרי פארמה/תרופות).
במדעי המחשב, יש בדרך כלל 30 פיבוטים שמפרידים בין הרעיון הראשוני למוצר הסופי שנובעים מהשתנות הצורך של השוק ומהתהליך של Product-Market-Fit.
בחלק גדול מהמקרים מתחילים מרעיון אחד ועוברים לרעיון אחר לחלוטין (לעיתים אפילו בדומיין אחר לגמרי).

[8en N@$$! @ben_nassi]

@penlume I DM'ed you. Please consider submit a talk to @BlackHatEvents Europe 26. I am heading the crypto session so in case you are intersted send me an email ASAP.

[8en N@$$! @ben_nassi]

@0xcharlie Writing agents that trigger accidental cyber attacks 😝

[Mike Takahashi @TakSec]

New @zenitysec Labs podcast w/ @mbrg0 + @ben_nassi on where AI security is going next:

Prompt injection vs Promptware
AI worms
Coding agents as hacking tools
Agent supply-chain attacks
Prompt injection → RCE
AI security ownership
Why LLM refusals aren't security controls
AI vulnerability disclosure is broken
The coming “CrowdStrike moment” for AI

Full episode in comments 👇

[Cinthia @CinthiaP]

If you work anywhere near AI security, @ben_nassi is someone worth listening to.

He joins @zenitysec's @mbrg0 for the inaugural episode of 🎙️#InTheWild🎙️to talk AI worms, promptware, what’s coming next.

Tune In🎧

Spotify: https://t.co/K0FXkqBSe1
Apple: https://t.co/Uhmrnnc7nD

[8en N@$$! @ben_nassi]

A talk with a great friend on tech…

[Michael Bargury @mbrg0]

starting with @ben_nassi we talk about the real world ai security conf at Stanford, the best BlackHat talk opener ever staring Dumbledore, building an ai worm with GPT4 back in 2024, and the evolution of promptware

available now on youtube, spotify and apple pods
https://t.co/Y1P5u4B0k8

[8en N@$$! @ben_nassi]

@StAJect0r @PwnieAwards @mbrg0 @p1njc70r @tamirishaysh @supriza0 Congrats 🎈

[StAJect0r @StAJect0r]

Extremely happy to get a Pwnie!

Hacking Agentic Browsers was fun this year! Going to post some technical dives today!

[8en N@$$! @ben_nassi]

@wunderwuzzi23 Here is an alternative name (LL)MiTM

[8en N@$$! @ben_nassi]

@StAJect0r Good luck!

[clem 🤗 @ClementDelangue]

The first autonomous agent cyberattack is an unprecedented event that deserves unprecedented transparency. Today we’re sharing everything we can: a full technical timeline, an interactive replay, and how we used an open model to defend ourselves, so defenders everywhere can learn from it and prepare for what’s next.

https://t.co/uPxIpjW8Xn

[8en N@$$! @ben_nassi]

@ClementDelangue @BrodtOleg

[8en N@$$! @ben_nassi]

@the_yaniv מדהים

[8en N@$$! @ben_nassi]

@wunderwuzzi23 Just think about the implications of poisoning ExploitGym which is now known to be the benchmark started these series of events!

Think about the integrity we ask from the authors of the GitHub.