Arturo Villacañas @artuvillacanas
Interests: AI Safety & Security. Currently: @kasl_ai. Prev: @CISPA, @IMDEA_Software, @CCNCERT. 🏳️🌈 Joined January 2015-
Tweets31
-
Followers52
-
Following142
-
Likes228
Here's an idea: instead of making the research opportunity gap wider, support research initiatives in the Global South so that at least research at the *undergrad level* becomes more accessible and equitable.
Here's an idea: instead of making the research opportunity gap wider, support research initiatives in the Global South so that at least research at the *undergrad level* becomes more accessible and equitable.
Huge thanks to @satml_conf for their $2,500 travel grant to attend the conference in April! See you in Toronto! 🤗❤️🇨🇦
The debate on AI risks and need for legislation is a complex one and my own position is not exactly identical to anything any of the key players have already publicized. I will however list some points of concurrence. )Not that anyone asked.. 😅) I am fully supportive of…
The debate on AI risks and need for legislation is a complex one and my own position is not exactly identical to anything any of the key players have already publicized. I will however list some points of concurrence. )Not that anyone asked.. 😅) I am fully supportive of…
I'm really grateful to @QueerinAI for their help in funding my MSc fees. Also, thanks to everyone at @CISPA who has echoed the call for donations. Please, consider contributing to help reduce the barriers that prevent financially insecure queers from pursuing academic careers.
I'm really grateful to @QueerinAI for their help in funding my MSc fees. Also, thanks to everyone at @CISPA who has echoed the call for donations. Please, consider contributing to help reduce the barriers that prevent financially insecure queers from pursuing academic careers.
Myth: open foundation models are antithetical to AI safety. Fact: open foundation models are critical for AI safety. Here are three reasons why:
Ready to make the next step in your academic career? We have opened our call for Faculty (faculty.jobs.cispa.de) in Security, Privacy and Crypto as well as AI/ML. Here's the gist of being Faculty from your future colleagues:
🚨 I'm looking for a postdoc position to start in Fall 2024! My most recent research interests are related to understanding foundation models (especially LLMs!), making them more reliable, and developing principled methods for deep learning. More info: andriushchenko.me
Hello @KU_Leuven, nice to meet you! I will be here until this Friday, attending your summer school on the security and privacy of AI. If you are curious about what we @leaschnherr @thorstenholz @CISPA are doing in MLSec, DM me and let's grab a coffee.
Is anyone with a Ph.D. in CS or EE (defended between 2013 and 2020) interested in working at IMDEA Networks in Madrid? There are interesting funding opportunities. DM me for more information.
This year‘s international CISPA Summer School focusing on #SystemSecurity is offering one week of talks, hands-on sessions, discussions, and a social program. For the 6th edition of our annual scientific event, #CISPA is welcoming 48 participants from 14 different countries.
Strongly agree with @halvarflake here. Focus on things with lasting impact. There are many problems that need solving that provide the same level of technical detail and skill as exploit dev. that aren’t nearly as ephemeral. Some of these problems solve for those very exploits.
Strongly agree with @halvarflake here. Focus on things with lasting impact. There are many problems that need solving that provide the same level of technical detail and skill as exploit dev. that aren’t nearly as ephemeral. Some of these problems solve for those very exploits.
_AzureLily @AzureLily23266
16 Followers 564 Following
Evelyn_Wilson @EvelynWils16234
8 Followers 373 Following
Horizon Events @HorizonEvents9
11 Followers 270 Following Events consultancy dedicated to advancing R&D in AI safety
Francesco Pinto @FraPintoML
34 Followers 136 Following Francesco Pinto, University of Oxford, PhD student TVG. Trustworthy and Privacy-Preserving ML Email: [email protected]
Reshmi Ghosh @reshmigh
1K Followers 2K Following ML / GenAI (+Jailbreaks) research for Responsible AI & Productivity, @Microsoft AI, @WiMLDS| Ph.D. @CarnegieMellon, @UMich | making AI trustworthy | She/Her
La Bestia Equilátera @labestiae
33K Followers 36K Following Editorial argentina. Siempre habrá alguna obra maravillosa que todavía no fue descubierta, no se tradujo o ni siquiera comenzó a escribirse.
Stephan Rabanser @steverab
382 Followers 316 Following PhD candidate @UofT and @VectorInst - reliable, safe, trustworthy machine learning
Augustin Godinot @augodinot
92 Followers 310 Following Algorithm Auditing | CS PhD student @ INRIA/IRISA/PEReN
Ahmed Jafri @ahmedjafrii
97 Followers 235 Following Engineering @ FB. AI Security. Opinions are my own
Krueger AI Safety Lab @kasl_ai
253 Followers 51 Following We are a research group at the University of Cambridge focused on avoiding catastrophic risks from AI.
Krystof Mitka @krystof_mitka
114 Followers 512 Following Currently completing undergraduate double degree in Applied Mathematics and Computer Science in 🇳🇱
jonathan | ヨナタ�.. @lostoxygen_
35 Followers 421 Following computer magician and passionate ramen eater. i try to break stuff on purpose | 24 | he/him
Poolesl @poolesl79459
39 Followers 665 Following
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
Siwoash @Siwoash179809
139 Followers 2K Following
Becky Martinez @BeckyMarti69244
128 Followers 3K Following
Javier Rando @javirandor
903 Followers 589 Following Red-Teaming LLMs | PhD Student @ETH_AI_Center | Incoming intern @Meta | Vegan 🌱
Aaron Criswell @ML_Moron
73 Followers 369 Following Interested in security for AI and AI for security. Background in cybersecurity.
Catherine Martinez @CatherineM5519
125 Followers 3K Following
Anthony Orji @ocanthony4real
219 Followers 929 Following Data Analyst | Data Visual Storyteller | Crazy with Power BI, Excel, SQL, and Python 💻
Peytetee @peytetee90378
189 Followers 3K Following
Sotout @Sotout194254
153 Followers 3K Following
Shoteaus @shoteaus28259
200 Followers 3K Following
David Krueger @DavidSKrueger
13K Followers 4K Following Cambridge faculty - AI alignment, deep learning, and existential safety. Formerly Mila, FHI, DeepMind, ElementAI, AISI.
Aleksandar Bojchevski @abojchevski
1K Followers 2K Following Trustworthy Machine Learning. Graphs. Professor at the University of Cologne. He/Him. 🏳️🌈 Open PhD/PostDoc positions: https://t.co/QSCqXRzlEu
Andrea Mengascini @CtrlAltAndrea
85 Followers 670 Following Ph.D. Student @CISPA Helmholtz Center for Information Security / Saarland University.
Adrián Javaloy @javaloyML
670 Followers 1K Following PhD student @SIC_Saar. Previously visitor @InfAtEd and student @MPI_IS @UMU.
Andrea Saunders @SaundersAn1743
48 Followers 387 Following
vscc 🏳️🌈 @vsccvscc
175 Followers 935 Following Neurosci of sexual diversity: sexual behaviomic, steroid independence, collective behaviour, lekking, wildlife animal, camera trap, stem cell, gene editing 🌈
LeomaBeskom @LeomaB72273
97 Followers 2K Following
Silvia Sebastián @silvi_sebastian
43 Followers 47 Following PhD Candidate (UPM) at IMDEA Software Institute 👩🏻💻: https://t.co/MyGFJ032HB 🎓: https://t.co/0m3nK5Z1Zu
Ali Abbasi @AlixAbbasi
2K Followers 1K Following Faculty at @CISPA. Research on embedded systems security. Mastodon: [email protected]
Sahar Abdelnabi 🍉�.. @sahar_abdelnabi
584 Followers 462 Following She/her. AI Security Researcher at Microsoft Security Response Center (MSRC) | prev. PhD @CISPA | Neurodivergent 🧠🦋 | peace for all #CeasefireNOW
José Antonio Zamudio @joszamama
63 Followers 199 Following Doctoral Researcher at CISPA Helmholtz Center for Information Security - Ph.D. Student at Universität des Saarlandes - R&D (Systems Security)
Maura Pintor @maurapintor
437 Followers 515 Following Assistant Professor @univca. Computer Science, Engineering, and Futsal lover.
Giovanni Cherubin @gchers
427 Followers 430 Following I research ML and (its) security/privacy @MSFTResearchCam & @msftsecresponse. May rant for hours about climbing/openbsd/rust/conformal prediction/ctfs
Battista Biggio @biggiobattista
3K Followers 2K Following Full Professor at University of Cagliari (Italy), Co-Founder of Pluribus One. #Security of #MachineLearning, #CyberSecurity & #ComputerVision
Lorenzo @LorenzoCazz
237 Followers 621 Following PhD student in Computer Science @CaFoscari | Previously at @CISPA | Adversarial Machine Learning, Verification of Machine Learning and AI for Security
Xin'an Emmanuel Zhou @zhouxinan
574 Followers 603 Following A 🏳️🌈 Computer Security PhD candidate at @UCRiverside.
Mauro Conti @mauroconti_
663 Followers 1K Following IEEE Fellow | Full Professor @UniPadova | Affiliate Prof. @TUdelft and @UW Seattle
Hannah @HEchenoz
1K Followers 369 Following Researcher & Faculty @UCBerkeley @CISPA @LIGLab @Inria @ncataggies;Alum @Columbia. NetSys| Wireless |5G| XR | HCI | Edge |Comp. Linguist |RL. Twin: @HaniaBP
Moritz Schloegel @m_u00d8
797 Followers 637 Following Security researcher & PhD student @CISPA / @ruhrunibochum @[email protected]
Narseo Vallina @narseo
2K Followers 955 Following Asturian. Research Associate Professor at @IMDEA_Networks & Co-Founder of @AppCensusInc. Previous: Researcher at @ICSIatBerkeley, Ph.D. @Cambridge_Uni.
Giacomo Santato @GiacomoSantato
43 Followers 80 Following Cryptography PhD student @ CISPA 🇩🇪 | Love to study FHE and PQ | Fellow Italian mathematician 🇮🇹🇳🇱
Antonio Nappa @jeppojeps
557 Followers 343 Following UC3M - Zimperium Inc. scholar, inventor. FWIW opinions are my own. Author of Fuzzing Against the Machine - https://t.co/Wf37lLx9fu
Siméon @Simeon_Cps
7K Followers 1K Following Creating more common knowledge on AI risks, one tweet at a time. Founder in Paris. AI auditing, standardization & governance.
Kayo Yin @kayo_yin
8K Followers 560 Following PhD student @berkeley_ai @berkeleynlp working on interpretability and signed languages. Former @msftresearch @deepmind @carnegiemellon @polytechnique. 🇫🇷🇯🇵
Technical AI Safety C.. @tais_2024
133 Followers 28 Following On 5th-6th April 2024, TAIS will bring together leading AI safety experts in Tokyo to discuss how to make AI safe, beneficial, and aligned with human values.
El Mahdi El Mhamdi | .. @L_badikho
13K Followers 597 Following Ass Prof @polytechnique. Past: Senior research scientist @Google & cofounder @mamfakinch. Book: Le Fabuleux Chantier, @EDPSciences 2019. Secular republican.
Ofir Press @OfirPress
10K Followers 3K Following I build tough benchmarks for LMs and then I get the LMs to solve them. Postdoc @Princeton. PhD from @nlpnoah @UW. Ex-visiting researcher @MetaAI & @MosaicML.
Sílvia Casacuberta @SiCaPu
673 Followers 2K Following Computer Science at @UniofOxford with @rhodes_trust. Previously: @Harvard ‘23, @CSatETH, @IBMResearch. Interested in theoretical CS, privacy & fairness.
Lucas Beyer (bl16) @giffmana
56K Followers 446 Following Researcher (Google DeepMind/Brain in Zürich, ex-RWTH Aachen), Gamer, Hacker, Belgian. Mostly gave up trying mastodon as [email protected]
Erik Bernhardsson @bernhardsson
38K Followers 3K Following Building @modal_labs when I'm not posting bangers about data and software. Previously built the music rec sys at Spotify and ran the eng team at Better.
Soumith Chintala @soumithchintala
186K Followers 883 Following Cofounded and lead @PyTorch at Meta. Also dabble in robotics at NYU. AI is delicious when it is accessible and open-source.
Mark Tenenholtz @marktenenholtz
114K Followers 544 Following Head of AI @PredeloHQ. XGBoost peddler, transformer purveyor.
Chip Huyen @chipro
92K Followers 444 Following Data processing on GPUs @VoltronData Designing ML Systems: https://t.co/G81hL2dWmr @designmlsys #AI x #GPU
VMware @VMware
327K Followers 648 Following VMware is a leading provider of multi-cloud services for all apps, enabling digital innovation with enterprise control. Also follow @vmwarenews.
MLflow @MLflow
9K Followers 43 Following An open source machine learning platform for managing the complete ML lifecycle
chrisrohlf @chrisrohlf
11K Followers 783 Following 🇺🇸 Waging algorithmic warfare since 2003. Software and Security Engineer. Non-Resident Research Fellow @CSETGeorgetown CyberAI
Rohan Pandey (e/acc) @khoomeik
3K Followers 1K Following multimodal codegen @ReworkdAI (YC S23+AIG3) || prev research @Microsoft + @CarnegieMellon '23 || 10x hackathon winner || living @AGIHouseSF
Finnish Center for AI.. @FCAI_fi
4K Followers 400 Following FCAI (Suomen tekoälykeskus): #RealAI for Real People in the Real World. Research from @AaltoUniversity @HelsinkiUni @VTTFinland & industry+society partners.
CambridgeEllisUnit @CambridgeEllis
964 Followers 172 Following The mission of the Cambridge ELLIS unit is to build on the excellent machine learning and AI infrastructure available within the University of Cambridge.
National Institute of.. @NIST
87K Followers 533 Following NIST promotes U.S. innovation & competitiveness by advancing measurement science, standards & tech to enhance economic security & improve our quality of life.
RAND @RANDCorporation
251K Followers 755 Following We help improve policy and decisionmaking through research and analysis. We're nonprofit, nonpartisan, and committed to the public interest.
Gabriel Mukobi @gabemukobi
337 Followers 316 Following @RANDCorporation, @Berkeley_AI | AI Governance, Safety, and Alignment
VirusSign @virussign
553 Followers 2 Following Cyber Threat Intelligence Hub. Giant crowdsourced malware database for cybersecurity. Rapidly collect, analyze emerging threats, generate intelligence with AI.
Trail of Bits @trailofbits
32K Followers 247 Following We help secure the world’s most targeted organizations and products. We combine security research with an attacker mentality to reduce risk and fortify code.
Robust Intelligence @robusthq
2K Followers 67 Following Achieve AI security and safety to unblock the enterprise AI mission.
Corelight @corelight_inc
4K Followers 645 Following Corelight transforms network and cloud activity into evidence so that data-first defenders can stay ahead of ever-changing attacks.
GitHub Security Lab @GHSecurityLab
26K Followers 15 Following GitHub Security Lab’s mission is to inspire and enable the community to secure the open source software we all depend on.
Microsoft Security @msftsecurity
352K Followers 338 Following A new era of cybersecurity is here. Explore Microsoft Copilot for Security today.
SentinelOne @SentinelOne
52K Followers 1K Following ONE autonomous platform to prevent, detect, respond, and hunt. Do more, save time, secure your enterprise: https://t.co/N75g1HAnCs 🐱💻
GreyNoise @GreyNoiseIO
28K Followers 152 Following GreyNoise analyzes Internet background noise. Use GreyNoise to remove pointless security alerts, find compromised devices, or identify emerging threats.
LABScon @labscon_io
2K Followers 752 Following Sept 18-21, 2024 - Scottsdale, Arizona CFP is open! https://t.co/Xj6aFUzGKZ
Antonio Orvieto @orvieto_antonio
1K Followers 1K Following Deep Learning PI @ELLISInst_Tue, Group Leader @MPI_IS. I compute stuff with lots of gradients 🧮, I like Kierkegaard & Lévi-Strauss 🧙♂️
Rafael Rafailov @rm_rafailov
3K Followers 637 Following Ph.D. Student at @StanfordAILab. I work on Foundation Models and Decision Making. Previously @GoogleDeepMind @UCBerkeley
Frank Nielsen @FrnkNlsn
23K Followers 1K Following Machine Learning & AI, Information Sciences & Information Geometry, Distances & Statistical models, HPC. "Geometry defines the architecture of spaces" @SonyCSL
Fusion Intelligence C.. @stealthmole_int
122K Followers 3K Following StealthMole : #Criminal #Intelligence #Profiling #Investigation Platform, #OSINT #DarkWeb #DeepWeb #Leaked #DataBreach #Terror #Drugs #Cryptoassets #Ransomware
Giskard @giskard_ai
4K Followers 3K Following 🐢 The #Testing framework for #AI models. Protect your company against biases, performance issues & security vulnerabilities in AI models. In 10 lines of code.
BINARLY🔬 @binarly_io
3K Followers 339 Following ⛓️Binarly is the world’s most advanced automated software supply chain security platform.
Marcel Böhme👨�.. @mboehme_
5K Followers 978 Following Software Security @maxplanckpress (#MPI_SP), PhD @NUSComputing, Dipl.-Inf. @TUDresden_de Research Group: https://t.co/BRnFNNgynB
Perri Adams @perribus
6K Followers 998 Following @DARPA — https://t.co/YcNwJRDMH6 #AIxCC | Prev @DEFCON CTF | @RPISEC Alumna | Opinions my own
Martijn de Vos @devos50
763 Followers 205 Following Postdoctoral researcher at EPFL working on decentralized machine learning. Interested in decentralized/distributed systems and reverse engineering.
Sebastian Raschka @rasbt
267K Followers 906 Following Machine learning & AI researcher writing at https://t.co/A0tXWzG1p5. LLM research engineer @LightningAI. Previously stats professor at UW-Madison.
Nathan Lambert @natolambert
25K Followers 690 Following Figuring out AI @allen_ai, "rl boi" DM me papers. Writes @interconnectsai, talks @retortai Has phd and some credentials
AI Village @ DEF CON @aivillage_dc
5K Followers 511 Following Hackers, ML researchers, and data scientists focused on the use and abuse of AI; join us! Discord: https://t.co/XljmSXRZii Twitch: https://t.co/7OcrkYd5xM
Michael Cohen @Michael05156007
1K Followers 144 Following I do AGI Safety research. https://t.co/CBsX51tA39. Once I was swiss chard for Halloween. Once Bill Clinton elbowed me in the face.
Will Merrill @lambdaviking
2K Followers 569 Following Ph.D. student @ NYU🗽 Theoretical aspects of NLP and LMs /nætʃɹəl/🇮🇸 + formal🤵 languages + TCS🧮
🚀Excited to share new work analysing how fine-tuning works mechanistically: arxiv.org/abs/2311.12786 We show that fine-tuning only produces limited “wrappers” on pretrained model capabilities, and these wrappers are easily removed through pruning, probing or more fine-tuning!
Couple of weeks ago I missed the @satml_conf which I had the pleasure to chair with @NicolasPapernot as I am too 🤰 to cross the Atlantic. Then I received this package signed by many atendees ❤ who said chairing is not rewarding? Thanks everyone! #BestCommunity
Introducing the Instruction Hierarchy, our latest safety research to advance robustness for prompt injections and other ways of tricking LLMs into executing unsafe actions. More details: arxiv.org/abs/2404.13208
Super excited to share that I successfully defended my PhD thesis "Understanding Generalization and Robustness in Modern Deep Learning" today 👨🎓 A huge thanks to the thesis examiners @SebastienBubeck, @zicokolter, and @KrzakalaF, jury president Rachid Guerraoui, and, of course,…
Tobias is SUUUUUUUPER skilled, if you are looking for a "one of a kind" course on fuzzing non-linux firmware fuzzing with things like unicornAFL, this is your guy 🔥
Our training on fuzzing custom firmware @typhooncon is coming up. This is a rare opportunity to learn about finding vulnerabilities in non-Linux firmware, which can be hard to get into. Get a chance to attend our training that was fully booked @hardwear_io typhooncon.com/blog/conitems/…
Excited to share Penzai, a JAX research toolkit from @GoogleDeepMind for building, editing, and visualizing neural networks! Penzai makes it easy to see model internals and lets you inject custom logic anywhere. Check it out on GitHub: github.com/google-deepmin…
Proud to start this month as a research fellow at 🟪@RANDCorporation to advance technical AI governance and in the fall as a CS PhD student at 🐻@UCBerkeley advised by @JacobSteinhardt and @dawnsongtweets! 🏛️I'm also in Washington, DC, until late August if anyone wants to meet!
The kids are alright
Proving once again that Minecraft exploits are fundamentally more interesting than the ones targeting software people actually care about (and definitely being better for civil society): github.com/spawnmason/ran…
As my time at @Mila_Quebec comes to an end, I’m excited to start my PhD journey later this year at @MPI_IS and @ELLISInst_Tue as an ELLIS PhD Fellow under the supervision of @orvieto_antonio. Bundesliga was also a key factor in this decision lol.
We have a new preprint out - your language model is not a reward, it’s a Q function! 1. The likelihood of the preferred answer must go down - it’s a policy divergence 2. MCTS guided decoding on language is equivalent to likelihood search on DPO 3. DPO learns credit assignment
You had to expect this was coming... LLaMA 3 solves a reverse engineering challenge (Baby's Third) with tool use! asciinema.org/a/655285
✨Excited to finally drop our new paper: SSMs “look like” RNNs, but we show their statefulness is an illusion🪄🐇 Current SSMs cannot express basic state tracking, but a minimal change fixes this! 👀 w/ @jowenpetty, @Ashish_S_AI arxiv.org/abs/2404.08819
Very grateful to @ERC_Research and @NWOFunding for both the ERC Advanced Grant and the NWO Gravitation Grant. (Anyone interested in a PhD or PostDoc in systems security / microarchitectural vulnerabilities, there is a lot of money for research at @vu5ec !)
Two (out of 8) things that @sleepinyourhat wants you to know about LLMs: (i) LLMs predictably get more capable with increasing investment (ii) Many important LLM behaviors emerge unpredictably How can we get ahead of the curve and predict these ‘unpredictable’ behaviors?🧵⬇️
I’m super excited to release our 100+ page collaborative agenda - led by @usmananwar391 - on “Foundational Challenges In Assuring Alignment and Safety of LLMs” alongside 35+ co-authors from NLP, ML, and AI Safety communities! Some highlights below...
Super excited about the release of this 🔥agenda paper on “Foundational Challenges in Assuring Alignment and Safety of LLMs!” that has been described as ‘particularly comprehensive' and 'epic piece of work' in private reviews. 😅
I’m super excited to release our 100+ page collaborative agenda - led by @usmananwar391 - on “Foundational Challenges In Assuring Alignment and Safety of LLMs” alongside 35+ co-authors from NLP, ML, and AI Safety communities! Some highlights below...
Usman deserves so much credit for leading and organizing this effort! It's been a long haul, but I'm really happy with the result!
Super excited about the release of this 🔥agenda paper on “Foundational Challenges in Assuring Alignment and Safety of LLMs!” that has been described as ‘particularly comprehensive' and 'epic piece of work' in private reviews. 😅
Happy to be part of the community and humbled for having received this notable reviewer award.
A research community is only as strong as its members. That's why #SaTML2024's indebted to our PC, esp these ten members who went beyond the call of duty: @asia_biega @mlsec @gchers Jamie Hayes @UdacityDave @zakynthinou @AlinaMOprea @DavidSKrueger @RyanSheatsley @fraboeni
Here's an idea: instead of making the research opportunity gap wider, support research initiatives in the Global South so that at least research at the *undergrad level* becomes more accessible and equitable.
This year, we invite high school students to submit research papers on the topic of machine learning for social impact! See our call for high school research project submissions below. buff.ly/43TiTdD
Really excited to co-chair @satml_conf 2025 with @mlsec We are really committed to keep growing this community. Please send email to me or Konrad if you have suggestions.
The 2nd edition of @satml_conf is a wrap! It was an absolute honour to co-chair the conference with @carmelatroncoso ! We are very excited to announce the co-chairs for the 3rd edition in 2025: @jhasomesh and @mlsec Follow @satml_conf for updates about the conference!
(How) can offensive security researchers estimate likely real-world impact of vulnerabilities they discover? I'm organizing a workshop (w/ @shw3ta_shinde and Kari Kostiainen, supported by @CHelveticum) hoping to start a cross-disciplinary conversation. medium.com/@asokan.public…
Trends for United States
You might like
