dreadnode @dreadnode
AI Red Teaming | Research. Tooling. Evals. Cyber ranges. dreadnode.io Joined August 2010-
Tweets12
-
Followers770
-
Following20
-
Likes14
I took an early stab at PGD for LLMs based on arxiv.org/abs/2402.09154 (@geisler_si). Neat technique to relax the one-hot for gradient updates + projection. Also got to spend some time with litgpt. github.com/dreadnode/rese… Experimental and messy, but enjoy.
The first big update is live inside Crucible. New dashboard, never before seen challenges, progress tracking, walkthroughs… Go check it out! crucible.dreadnode.io
Announcing our newest crew member, @Rob_Mulla as Head of Data Science. His professional journey highlights an intense curiosity for new problems. At Dreadnode, he continues his journey in Offensive Security. Welcome, Rob. linkedin.com/posts/dreadnod…
We've been on the road this last month - please enjoy the slides we can share, including a small workshop we gave @ApresCyber github.com/dreadnode/conf…
The most common ask we got after the @aivillage_dc CTF on @kaggle was to make the challenges available all the time. We took our first steps today and look forward to building out a great ML CTF and learning platform. Hope you enjoy!
The most common ask we got after the @aivillage_dc CTF on @kaggle was to make the challenges available all the time. We took our first steps today and look forward to building out a great ML CTF and learning platform. Hope you enjoy!
Was an awesome training environment. Props to @SpecterOps for the work they’ve put into their RTO course. So. Much. Content. Would highly recommend to all aspiring red teamers.
Was an awesome training environment. Props to @SpecterOps for the work they’ve put into their RTO course. So. Much. Content. Would highly recommend to all aspiring red teamers.
Come see what we’ve been working on!
Come see what we’ve been working on!
Minimal implementation of the Tree of Attacks (TAP) LLM jailbreaking from @robusthq: github.com/dreadnode/parl… - Cleaned + updated the prompts - Uses OpenAI, Mistral, and TogetherAI APIs - Refactored the leaf branching strategy
Is this the world's first AI pentest company @dreadnode? Run by two of best guys in the industry @moo_hax @monoxgas enjoy the presents coming tomorrow morning!
We're live! Dreadnode is all about AI red teaming and offensive ML. Founders are @moo_hax and @monoxgas. Follow us for research, tooling, evals, and challenges. dreadnode.io Let the real hacking begin.
Mimi Litty @litty_mim
36 Followers 4K Following
Cecilia Gorius @CeciliaGor51410
74 Followers 5K Following
Th0h0 @Th0h0
96 Followers 319 Following Hunting web vulnerabilities. Cyber Security MSc @ETH - currently on semester leave.
sink0Rswim @laceandload
106 Followers 2K Following
Chandler Ward @chandlerjward
240 Followers 1K Following Building in Stealth (Fintech / Proptech) | Prior @batteryventures | @BYU alum | views expressed here are my own
Harrison Van Riper @pseudohvr
597 Followers 447 Following ▶️ Founder, Zero-Shot Security (@zeroshotsec) ⏮ @RedCanary ⏮ @MITREattack ⏮ @DigitalShadows ~ Robo wants an Oreo
Zambrano @workforfood
9K Followers 2K Following Founder of CREME® → a food company that combines media & technology to rebuild our relationship with food → @letscreme
John skiing the gnar @turboCodr
705 Followers 758 Following Working in the intersection of Data Science & InfoSec / I know more about x509 and TLS than your average person out walking their cat
Yoni Rozenshein @1yoni
275 Followers 388 Following Security, internals, cryptography, math, and AI. Monitoring LLM cyber capabilities at Pattern Labs.
Tyler Duquette @indlabs
23 Followers 181 Following
Gesny Enoal @EnoalGesny
0 Followers 10 Following
Steve Taggart @stevotaggart
80 Followers 593 Following Software Engineer. Lifelong learner, musician, husband, father. He/him. Organizing board member of the SLC .NET user group (https://t.co/9dKxt5qepR)
Bug Hunter Labs @BugHunterLabs
570 Followers 609 Following
The Digital Voyage @thedigitalvoya1
509 Followers 1K Following Here for the open metaverse ASM / Fluf / Party Bears.
Alan @alansteer
21 Followers 248 Following
Ankur @Ankuryogi11
251 Followers 4K Following Data and Engineering ....................... A breathing creature on planet earth The true power of science is bruteforce .Stop fitting inn
A V @hypn0
263 Followers 5K Following
pablito.eth 🦇🔊 .. @PabloSabbatella
69K Followers 4K Following Head of Security research @Blockfence_io . @_SEAL_Org member . Ethereum, DeFi, OpSec & Blockchain security. @DefyEducation founder. @EtherArgentina co-founder.
researcher Gpt LLM @researchGptllm
231 Followers 4K Following
cyberresponder @Malwarenailed
290 Followers 3K Following tweets and opinions are my own. dfir/threat hunting/malware research
Ashutosh Kumar Singh @0xAshutosh
14 Followers 432 Following 💻 Software Engineer & Security Enthusiast • exploring new Technologies • Passionate Coder 🔥 | 3x GCP | AI Enthusiast,Opensource ask me about DevOps & Security
Anshul Gupta @j4ck4l_24
19 Followers 57 Following CTF-Player and Web Security @InfoSecIITR 2nd year Electrical Engineering student @iitroorkee
Blingblong @blingblongsyst
136 Followers 1K Following
Miriam Douglas @MDouglas23583
20 Followers 712 Following
Mathéo @Matho21969795
2 Followers 349 Following
jingy @jingylol
13 Followers 77 Following
shxdow @shxdowtc
411 Followers 736 Following msc computer engineering • browsers • compilers • reverse engineering • program analysis • @osec_io • mastodon: https://t.co/wRm4sr6h9B
Sachit Malik @isachitmalik
176 Followers 3K Following
aespa(x) @aespa__init
18 Followers 236 Following A certain scientific GPU accelerator. Work in tech but not technical. Ex: anime, gaming. Math challenged. Trying to learn ML.
birdbutt @wopcopter
0 Followers 2K Following
Jules G @JulesGoullee
313 Followers 5K Following Self-destructing, but creating too . . . Formerly at selfdestruct() create2(0, add(bytecode, 0x20), mload(bytecode), salt)
Struct (he/him) @tackvector
156 Followers 537 Following Advanced positive threat. Not always here but always near. Welcome to the chat.
Brendan Dolan-Gavitt @moyix
25K Followers 6K Following Associate Professor @ NYU Tandon. Security, RE, ML. PGP https://t.co/3WXr0RfRkv Founder of the MESS Lab: https://t.co/zGycrX3Gmn "an orc smiling into the camera" — CLIP
Suha @suhackerr
366 Followers 519 Following ML security @trailofbits. Opinions not representative of my employer. She/Her. (@[email protected])
Rob Haisfield (robhai.. @RobertHaisfield
7K Followers 3K Following Imagining new internets @websim_ai. GenAI, TfT, BeSci, HCI, UX. Ex-Tana, Edge & Node, Spark Wave
shane caldwell @shncldwll
352 Followers 259 Following pentester + ml eng. building hackbots @runsybil
Rich Harang @rharang
3K Followers 703 Following Using bad guys to catch math since 2010. Principal Security Architect (AI/ML) at NVIDIA. He/him. Personal account and opinions: `from std_disclaimers import *`.
Allan is @allanfriedm.. @allanfriedman
7K Followers 2K Following #SBOM Champion. Full service technocrat. Now at @CISAgov, formerly NTIA. Lapsed{engineer, academic, author}. Personal Account.
Chris Albon @chrisalbon
86K Followers 2K Following Director of Machine Learning at the Wikimedia Foundation. We host Wikipedia.
SpecterOps 🇺🇦 @SpecterOps
36K Followers 378 Following Know Your Adversary - Adversary Simulation | Detection | Resilience
Tri Dao @tri_dao
19K Followers 365 Following Incoming Asst. Prof @PrincetonCS, Chief Scientist @togethercompute. Machine learning & systems.
Rob @Rob_Mulla
5K Followers 560 Following Data Science @ https://t.co/obcGxNNJSg // Python 🐍 & Data 💾 // 4x Kaggle Grandmaster // Live coding is fun 🎙️// Follow on twitch: https://t.co/GHjWoRVia7 & Youtube: https://t.co/WfD4vK0age
Giorgio @cloned_tweets
178 Followers 545 Following on the internet nobody knows you're a sloth occasionally also a cs phd student doing evil numerical optimization
Amanda M @NMspinach
344 Followers 190 Following Senior ML Researcher on the AI Red Team @ Microsoft. ex-Tweep. Opinions my own.
Will Schroeder @harmj0y
46K Followers 938 Following Researcher @SpecterOps. Coding towards chaotic good while living on the decision boundary.
Lee Chagolla-Christen.. @tifkin_
13K Followers 812 Following I like making computers misbehave. Does stuff at https://t.co/YsrVyTjOY7. Mastodon: @[email protected]
Stella Biderman @BlancheMinerva
15K Followers 748 Following Open source LLMs and interpretability research at @BoozAllen and @AiEleuther. My employers disown my tweets. She/her
monoxgas @monoxgas
4K Followers 353 Following Security research, exploits, malware dev, training. Co-Founder with @moo_hax at @dreadnode
moo @moo_hax
3K Followers 1K Following Security researcher, Co-Founder @dreadnode | @microsoft @nvidia
Dan Shaw @dshaw
19K Followers 7K Following @Ethereum business. Former EF. 🦄 Founded @NodeSource. @nodejs OG. ✨
lol Fastly glad they banned red teams though
"...results reveal that domain fronting is feasible in 22 out of 30 CDNs tested, including some major CDN providers like Akamai and Fastly. This indicates that domain fronting remains widely available & can be easily abused for malicious purposes" -great😐 arxiv.org/abs/2310.17851
I took an early stab at PGD for LLMs based on arxiv.org/abs/2402.09154 (@geisler_si). Neat technique to relax the one-hot for gradient updates + projection. Also got to spend some time with litgpt. github.com/dreadnode/rese… Experimental and messy, but enjoy.
It's a big day- @tifkin_, @0xdab0, and I are proud to announce that Nemesis 1.0.0 has landed! We have a ton of awesome new features and a streamlined installation, check out the details at posts.specterops.io/nemesis-1-0-0-… and the code at github.com/SpecterOps/Nem…
Huge update for Nemesis. We're finally v1.0.0!!!
It's a big day- @tifkin_, @0xdab0, and I are proud to announce that Nemesis 1.0.0 has landed! We have a ton of awesome new features and a streamlined installation, check out the details at posts.specterops.io/nemesis-1-0-0-… and the code at github.com/SpecterOps/Nem…
I know LLMs and image models have all the hype right now, but transformers and diffusion can do so much more, especially in specialized areas. There's more than chatbots and weird hands out there. build.nvidia.com/explore/biology
You had to expect this was coming... LLaMA 3 solves a reverse engineering challenge (Baby's Third) with tool use! asciinema.org/a/655285
1. NVIDIA believes the competition is strong and getting stronger - as it should, since AI is the largest computational problem in history. 2. Accelerated computing is mostly not hardware. I’m surprised people still see NVIDIA’s business as hardware, after all these years.
For example, I can't imagine anyone at Google saying this in 2005, or anyone at Microsoft saying it in 1995. They might have hoped it, but they wouldn't have said it. Maybe hardware has more moats. Maybe this guy is just outspoken. But either way, this is a rare type of claim.
@LeonDerczynski I'd go so far as to say that *most* of the stuff popping up in academic papers these days as novel research w/r/t LLM security has been widely known among practicioners for a year or more. Normalize citing blog posts and non-academic work, and not just "citable" papers.
Also, a fun sidenote on RPC security is noted in the wiki ;) github.com/EvanMcBroom/ls…
Incredibly cool talk showing that @AntithesisHQ can autonomously solve Super Mario Brothers 1, including finding Minus World! antithesis.com/blog/sdtalk/
The best single-track infosec + ML conference out there. If you're in that niche, you should be checking this out.
We are excited to share not one, but TWO exciting opportunities open for #CAMLIS2024 today! 🚀Call For Papers: camlis.org/call-for-papers 📚Student Scholarship Application: forms.gle/CdG1UUUoppsEMS… Submit and/or apply today!
HIIT morning done 💪 never sure if I’m gonna die or not mid class.. it’s that kinda gamble that makes you feel alive!
HOLY SHIT The websim_ai project is INSANE All generated on the fly by Claude and then rendered. Most interesting project all year. I'll be here all weekend. See you next week
Congrats to the team! Looking forward to a very near future where the question “where do you go to get spun up on ML hacking” is answered by “@dreadnode, duh”. Can’t wait to try it out this weekend.
Crucible beta is now open! Free for everyone. Come learn how to hack, evaluate, and work with ML systems in a safe hosted environment. crucible.dreadnode.io Be on the look out for new challenges and announcements as we expand our materials.
Either we achieve AGI or you’ll be able to pick up a used H100 for super cheap in a few years. Win-win in my book.
I think AI agentic workflows will drive massive AI progress this year — perhaps even more than the next generation of foundation models. This is an important trend, and I urge everyone who works in AI to pay attention to it. Today, we mostly use LLMs in zero-shot mode, prompting…
👀 @moo_hax with a little @dreadnode sneak peek…
I get to have another helping of "Ghosts on the Node" from @moo_hax / @monoxgas / @dreadnode here at @ApresCyber ! One of the coolest talks I've seen in years. "I don't know if you need more convincing but we're there." - @monoxgas
All slides for presentations at #SOCON2024 sponsored by @SpecterOps are now live! github.com/SpecterOps/pre…
I love LinkedIn because they blurred the code 😂
Trends for United States
You might like
