Sign in

Konrad Rieck 🌈

@rieck.mlsec.org
412 followers 114 following 46 posts

Machine Learning and Security, Professor of Computer Science at TU Berlin,

PostsRepliesMedia
Reposted by Konrad Rieck 🌈
Annual Computer Security Applications Conference @acsacconf.bsky.social · 22/04/2026
📣 The Call for Papers for #ACSAC2026 is out and the deadline for paper submissions is 26th May 2026 📣 You can find all the infos on the paper submissions and also the other types of possible submissions in the calls on our website:
acsac.org
Call for Papers - IEEE Annual Computer Security Applications Conference (ACSAC)
The IEEE Annual Computer Security Applications Conference (ACSAC) brings together cutting-edge researchers, with a broad cross-section of security professionals drawn from academia, industry, and government, gathered to present and discuss the latest security results and topics. With peer reviewed technical papers, invited talks, panels, national interest discussions, and workshops, ACSAC continues its core mission of investigating practical solutions for computer and network security technology.
011
Reposted by Konrad Rieck 🌈
BIFOLD Berlin Institute for the Foundations of Learning and Data @bifold.berlin · 23/04/2026
Offensive AI Is Here. Now What? Join us at the next BIFOLD Colloquium with Dr. Yisroel Mirsky (April 30, 2026; 4 PM; BIFOLD) More: t1p.de/tbqes @tuberlin.bsky.social
012
Reposted by Konrad Rieck 🌈
BIFOLD Berlin Institute for the Foundations of Learning and Data @bifold.berlin · 23/04/2026
We had the pleasure of welcoming a group of eleven curious and talented young women to BIFOLD for Girls' Day 2026. 🚀 Our participants dove headfirst into the world of computer science and IT security. @tuberlin.bsky.social #WomenInSTEM #Science #Girlsday #Zukunftstag
141
Reposted by Konrad Rieck 🌈
Lukas Pirch @lpirch.bsky.social · 18/04/2026
Code Metrics perform as well as LLM-based classifiers for source code vulnerabilities! I'm glad the community didn't shoot the messenger when I presented our recent work at ICSE'26. preprint: mlsec.org/docs/2026-ic... Shout out to Felix, Erik, Jonas, @eisenhofer.bsky.social and @rieck.mlsec.org
Lukas Pirch at ICSE'26 next to his title slide
041
Konrad Rieck 🌈 @rieck.mlsec.org · 18/04/2026
More here... (4/4) 📄 Paper: mlsec.org/docs/2026-icse.pdf 💻 Code: github.com/mlsec-group/cheetah
mlsec.org
010
Konrad Rieck 🌈 @rieck.mlsec.org · 18/04/2026
This leaves us confused. Apparently, much of recent progress comes from the agent and the tools around the LLM rather than any inherent capability to understand vulnerable code. Which raises the question: how much of that huge model is actually needed? (3/4)
110
Konrad Rieck 🌈 @rieck.mlsec.org · 18/04/2026
It's not just correlation. A causal analysis shows that when you change a metric value, LLM predictions shift proportionally. Despite their enormous size, these models are operating at the surface of the code, counting lines and loops 😢 (2/4)
100
Konrad Rieck 🌈 @rieck.mlsec.org · 18/04/2026
Yesterday, Lukas presented at #ICSE2026 results I didn't believe when he first showed them to me. A classifier based on simple code metrics matches frontier LLMs for vulnerability discovery in performance, as long as they are not agentic. 🧵 (1/4)
Paper: LLM-based Vulnerability Discovery through the Lens of Code Metrics
1112
Konrad Rieck 🌈 @rieck.mlsec.org · 18/04/2026
This sounds awesome! I hope you share some material for those who cannot attend ICST.
110
Reposted by Konrad Rieck 🌈
BIFOLD Berlin Institute for the Foundations of Learning and Data @bifold.berlin · 23/03/2026
BIFOLD supports IEEE SaTML 2026. 🧵 🔔Program Chair: Konrad Rieck, alongside Rachel Cummings 🔔Web Chair: @eisenhofer.bsky.social & Stefan Czybik 🔔Part of the Program Committee: Thorsten Eisenhofer, @kirillbykov.bsky.social @tuberlin.bsky.social @tumunich.bsky.social @rieck.mlsec.org @satml.org
142
Reposted by Konrad Rieck 🌈
Dez Fenton @butisitart.bsky.social · 22/03/2026
You know how in a library no one’s trying to sell you anything? That’s how the internet was.
268147302852
Reposted by Konrad Rieck 🌈
Dominik Herrmann @herdom.bsky.social · 21/03/2026
4 Jahre lang haben wir im Bayer. Forschungsverbund ForDaySec.de untersucht, wie IT-Sicherheit im Alltag funktioniert. Informatik, Soziologie und Recht, 5 Unis, 8 Teilprojekte. Am Mittwoch (25.3.) stellen wir die Ergebnisse in München vor. 1/2
111
Reposted by Konrad Rieck 🌈
Marco Di Gennaro @marcodige.bsky.social · 16/03/2026
📣 Our paper “On the (In)Security of Loading Machine Learning Models” has been accepted at IEEE S&P 2026 (13% acceptance rate this cycle). (1/5) 👇 Preprint: arxiv.org/abs/2509.06703 #ieeesp #ieeesp26 #ieee #cybersecurity #softwaresecurity #aisecurity #machinelearning #ml #zeroday
194
Reposted by Konrad Rieck 🌈
BIFOLD Berlin Institute for the Foundations of Learning and Data @bifold.berlin · 16/03/2026
#GirlsDay 2026 Join us at BIFOLD / @tuberlin.bsky.social Three hands-on stations await you in the world of data science & IT security. Register here 👉 t1p.de/2wwys #WomenInTech #WomenInSTEM #ComputerScience #cs
1147
Reposted by Konrad Rieck 🌈
BIFOLD Berlin Institute for the Foundations of Learning and Data @bifold.berlin · 12/03/2026
Congratulations to Prof. Dr. Volker Markl, Co-Director of BIFOLD, on being elected to the German National Academy of Sciences Leopoldina! BIFOLD News: t1p.de/1wsrz @tuberlin.bsky.social @dfki.bsky.social @leopoldina.org
161
Konrad Rieck 🌈 @rieck.mlsec.org · 13/03/2026
💭Ever dreamed of serving on the PC of one of the coolest security conferences in academia? Now is your chance. Nominate yourself and your capable friends for the Program Committee of @acsacconf.bsky.social 2026 🧑‍💻 forms.gle/SMbphtLggYcE...
forms.gle
ACSAC 2026 PC nomination
033
Reposted by Konrad Rieck 🌈
BIFOLD Berlin Institute for the Foundations of Learning and Data @bifold.berlin · 07/03/2026
Charité - Universitätsmedizin Berlin & BIFOLD are #hiring. #W3 #Professorship in Data Engineering in Health, permanent tenure. career.charite.de/calls/aussch... #AcademicSky #chariteBerlin #STEMjobs #academicjobs @tenuretracker.bsky.social #Medinformatics #ClinicalResearch @tuberlin.bsky.social
122
Konrad Rieck 🌈 @rieck.mlsec.org · 03/03/2026
First Stealth, now FX… Hug your people a little tighter. They won't be around forever.
030
Reposted by Konrad Rieck 🌈
joern @jrn.bsky.social · 02/03/2026
Lands of Packets TTL exceeded. I would like to collect texts from the scene about FX in his memory. A collection of obituaries that will then be posted on phenoelit.de. If anyone would like to contribute, please contact me. Mail: joernchen@phenoelit.de Signal: jrn.07
0167
Reposted by Konrad Rieck 🌈
Recurity Labs @recurity-labs.com · 02/03/2026
We wished we had more time to find the right words, and it is with deep regret that we have to tell you that our founder Felix “FX” Lindner passed away on 2026-03-01. blog.recurity-labs.com/2026-03-02/F...
blog.recurity-labs.com
Farewell, Felix · The Recurity Lablog
1128
Reposted by Konrad Rieck 🌈
BIFOLD Berlin Institute for the Foundations of Learning and Data @bifold.berlin · 11/02/2026
Today is the International Day of Women and Girls in Science (Feb 11, 2026). In our video, BIFOLD researchers provide brief insights into their research areas while voicing their support for diversity in scientific environments. @tuberlin.bsky.social #WomenInScience #DayOfWomenAndGirlsInScience
171
Reposted by Konrad Rieck 🌈
Christian Wressnegger @chwress.bsky.social · 28/01/2026
Although we had secretly planned a small extension, we realized that the initial deadline was off by one… month 😵‍💫 Thus, we are now extending the submission deadline for the "Explainable AI and Security" (XAISEC) workshop: 🌐 xaisec-workshop.org ⏱️Deadline: J̶a̶n̶ ̶2̶9̶t̶h̶ Feb 26th, 2026 (AoE)
023
Reposted by Konrad Rieck 🌈
dmnk @dmnk.bsky.social · 23/01/2026
The Cscript Style Guide just dropped. github.com/domenukk/CSc...
github.com
GitHub - domenukk/CScript: CScript is the standard C.
CScript is the standard C. Contribute to domenukk/CScript development by creating an account on GitHub.
051
Reposted by Konrad Rieck 🌈
Ana-Maria Cretu @ana-mariacretu.bsky.social · 20/01/2026
I am delighted to announce I have joined @cispa.de as a tenure-track faculty earlier this month! I’m really excited to join such a stellar team of security and privacy researchers!
2101
Reposted by Konrad Rieck 🌈
Moritz Schloegel @mu00d8.bsky.social · 19/01/2026
📣 Call for papers! If you're interested in all things metascience, consider submitting to the 1st Workshop on Metascience and Critical Reflections in Security & Privacy (MetaCRiSP), co-located with IEEE S&P. Deadline's Feb 12, AoE. CfP & details: metacrisp.org
metacrisp.org
MetaCRiSP 2026
152
Reposted by Konrad Rieck 🌈
BIFOLD Berlin Institute for the Foundations of Learning and Data @bifold.berlin · 19/01/2026
🎓 10 #PhD positions in #AI & #DataScience - #Berlin BIFOLD is hiring 10 PhD candidates in: 🤖 #MachineLearning 🗄️ #DataManagement 🔗 #ML × #DM Apply until Feb 13, 2026 www.jobs.tu-berlin.de/en/job-posti... @tuberlin.bsky.social @rieck.mlsec.org #AcademicSky #PhDSky #sciencejobs #academicjobs
173
Reposted by Konrad Rieck 🌈
Stefano Zanero @raistolo.bsky.social · 17/01/2026
Literally every single thing in here was astonishingly evident from the beginning.
24916
Reposted by Konrad Rieck 🌈
BIFOLD Berlin Institute for the Foundations of Learning and Data @bifold.berlin · 13/01/2026
We would like to extend our sincere thanks to the Senate delegation for visiting BIFOLD at TU Berlin and engaging so openly with our researchers and partners. @tuberlin.bsky.social @fraunhoferhhi.bsky.social @regberlin.bsky.social @xai-berlin.bsky.social www.linkedin.com/feed/update/...
041
Konrad Rieck 🌈 @rieck.mlsec.org · 12/01/2026
The Call for Papers for our Special Issue in IEEE Security & Privacy is finally out: Autonomous AI Agents in Computer Security www.computer.org/digital-libr... Deadline is May 1, 2026. We are looking forward to your exciting submissions.
computer.org
CFP: Special Issue on Autonomous AI Agents in Computer Security
We propose to explore the challenges, opportunities, and limitations arising from autonomous AI agents in computer security.
030
Reposted by Konrad Rieck 🌈
Andreas Zeller @andreaszeller.bsky.social · 08/01/2026
A researcher used more than 2,000 em-dashes in his papers, revealing AI-based manipulation in 400+ papers since 1985. Professor Zeller claims he "typed" these dashes into the paper by using "two hyphens" and a "typesetting" system.
$ cd ~/Papers/
$ grep -e '[ ~]-- ' */*.tex | wc -l
    2258
$
1181
Reposted by Konrad Rieck 🌈
Rodger Sherman @rodger.bsky.social · 02/01/2026
went back and grabbed the full video of her intro. absolutely incredible 🇮🇹🍝👩‍🍳🤌🇮🇹🍝👩‍🍳🤌🇮🇹🍝👩‍🍳🤌🇮🇹🍝👩‍🍳🤌
5242331117
Reposted by Konrad Rieck 🌈
Conference on Secure and Trustworthy Machine Learning @satml.org · 22/12/2025
Still no plans for March 2026? How about a pretzel and a beer in Munich 🥨🍺 Registration for SaTML is now open: satml.org/attend/ We have a packed program with papers on secure, private, and fair machine learning. Accepted papers here: satml.org/accepted-pap...
satml.org
IEEE SaTML 2026 · Attending the Conference
021
Reposted by Konrad Rieck 🌈
Conference on Secure and Trustworthy Machine Learning @satml.org · 21/12/2025
The accepted papers for SaTML 2026 are now online: satml.org/accepted-pap... Congratulations to all authors 🎉 and many thanks to everyone who submitted their work! This year, we received 233 submissions, of which 55 papers were accepted. A few revisions are still in the pipeline, so stay tuned.
satml.org
041
Konrad Rieck 🌈 @rieck.mlsec.org · 19/12/2025
Congrats
110
Reposted by Konrad Rieck 🌈
Marcel Böhme @mboehme.bsky.social · 18/12/2025
I have been named an ACM Distinguished Member for "contributions to software security and fuzz testing". Happy and honored! A heartfelt *Thank You* to my nominator and all of you who endorsed and supported me - today and throughout my entire career. 1/2
5294
Reposted by Konrad Rieck 🌈
BIFOLD Berlin Institute for the Foundations of Learning and Data @bifold.berlin · 12/12/2025
#ACSAC Test-of-Time Award @acsacconf.bsky.social awarded a Test-of-Time Award for "CUJO: Efficient Detection and Prevention of Drive by Download Attacks" (2010). K Rieck, T Krueger, A Dewald www.bifold.berlin/news-events/... @rieck.mlsec.org @tuberlin.bsky.social #MLSky #MLSecurity #AI
131
Reposted by Konrad Rieck 🌈
Annual Computer Security Applications Conference @acsacconf.bsky.social · 11/12/2025
Congratulations to the winners of #ACSAC2025's third test of time award: "Cujo: Efficient Detection and Prevention of Drive-By-Download Attacks" by Konrad Rieck, Tammo Krueger, and Andreas Dewald published in ACSAC 2010. 👏👏👏
053
Reposted by Konrad Rieck 🌈
Technische Universität Berlin @tuberlin.bsky.social · 11/12/2025
🎉 Herzlichen Glückwunsch, Klaus-Robert Müller! Der #TUBerlin- Wissenschaftler und Direktor von @bifold.berlin erhält den renommierten Leibniz-Preis der @dfg.de. Er gilt als Pionier des Maschinellen Lernens und prägt die interdisziplinäre #KI- Forschung seit Jahrzehnten. (1/2) Weiterer Infos 👇
tu.berlin
Leibniz-Preis für Klaus-Robert Müller
TU-Forscher und Co-Direktor des BIFOLD wird mit dem renommiertesten Forschungsförderpreis in Deutschland geehrt / Fördersumme 2,5 Millionen Euro.
1123
Reposted by Konrad Rieck 🌈
BIFOLD Berlin Institute for the Foundations of Learning and Data @bifold.berlin · 11/12/2025
Klaus-Robert Müller, Pioneer in Machine Learning, honored with the 2026 Gottfried Wilhelm Leibniz Prize by @dfg.de www.bifold.berlin/news-events/... @tuberlin.bsky.social #mlsky @xai-berlin.bsky.social #datascience #AI
0124
Reposted by Konrad Rieck 🌈
Dilyara Bareeva @dilya.bsky.social · 29/11/2025
Huge thanks to my fantastic co-authors Marina MC Höhne, Alexander Warnecke, @lpirch.bsky.social, Klaus-Robert Müller, @rieck.mlsec.org, @slapuschkin.bsky.social, @kirillbykov.bsky.social, and to the UMI Lab, @aifraunhoferhhi.bsky.social, @xai-berlin.bsky.social and @bifold.berlin for the support!
141
Reposted by Konrad Rieck 🌈
Dilyara Bareeva @dilya.bsky.social · 29/11/2025
Our lightweight adversarial fine-tuning attack lets you bend a feature to visualize any arbitrary concept. Off-manifold, we impose a hyperbolic activation landscape with its optimum at the target, while preserving on-distribution activations through a weighted two-term loss. 🕵️‍♀️
111
Reposted by Konrad Rieck 🌈
Dilyara Bareeva @dilya.bsky.social · 29/11/2025
✈️🇲🇽 Next Wednesday (Dec 3), 1–4 p.m. CST, I’ll be presenting Manipulating Feature Visualizations with Gradient Slingshots at NeurIPS 2025 in Mexico City! Feature Visualization has long been a staple interpretability tool. Our work shows it’s far from reliable! 🚨
194
Reposted by Konrad Rieck 🌈
Andreas Zeller @andreaszeller.bsky.social · 07/12/2025
Bonus material for The LaTeX Korrektor! Some of you asked: "What are these photos and posters in the background?" Here they come, enlarged and with some details. Enjoy! #LaTeX #LaTeXKorrektor In case you missed it, watch all six episodes of the LaTeX Korrektor here: www.youtube.com/watch?v=EhsM...
A description of the items shown in the LaTeX Korrektor background:

* Diomidis Spinellis
, Author of
 “Advice for writing LaTeX documents”
* LaTeX 2ε 
Cheat Sheet
* Helmut Kohl
, German Chancellor
 1982–1988
* A fictitious
 event poster "Lack Leder LaTeX, Hamburg"
* A fictitious
 LaTeX 
propaganda 
poster
162
Reposted by Konrad Rieck 🌈
Explainable AI Berlin @xai-berlin.bsky.social · 28/11/2025
Manipulating Feature Visualizations with Gradient Slingshots @dilya.bsky.social Marina MC Höhne, Alexander Warnecke @lpirch.bsky.social Klaus-Robert Müller @rieck.mlsec.org @slapuschkin.bsky.social @kirillbykov.bsky.social 👇
143
Reposted by Konrad Rieck 🌈
Marcel Böhme @mboehme.bsky.social · 03/11/2025
Gaetano's paper on Scaling Security Testing by Adressing the Reachability Gap has been accepted at #ICSE26! 📝 gpsapia.github.io/files/ICSE_2... 🧑‍💻 github.com/GPSapia/Reac... How to scale automatic security testing to arbitrary systems?
1175
Reposted by Konrad Rieck 🌈
Explainable AI Berlin @xai-berlin.bsky.social · 03/11/2025
This is the eXplainable AI research channel of the machine learning group of Prof. Klaus-Robert Müller at Technische Universität Berlin @tuberlin.bsky.social & BIFOLD @bifold.berlin. Let's connect! #XAI #ExplainableAI #MechInterp #MachineLearning #Interpretability
media.tenor.com
a black background with green text that says `` hello , world ''
ALT: a black background with green text that says `` hello , world ''
0236
Reposted by Konrad Rieck 🌈
BIFOLD Berlin Institute for the Foundations of Learning and Data @bifold.berlin · 31/10/2025
Congratulations to Dr. Jonas Dippel on successfully defending his doctoral dissertation titled “Towards Robust Generalizable Machine Learning Models for Computational Pathology.” @tuberlin.bsky.social
031
Reposted by Konrad Rieck 🌈
KIT Graduate School Cyber Security @kitcybersec.bsky.social · 29/10/2025
On Wednesday, November 5th, as part of our KASTEL Distinguished Lecture Series Prof. Gianluca Stringhini, PhD from Boston University will talk about ‘Improving the Moderation of False Information and Influence Campaigns on Social Media’. Everybody is welcome and stay around for the Q&A afterwards.
033
Reposted by Konrad Rieck 🌈
Andreas Zeller @andreaszeller.bsky.social · 28/10/2025
Today I turn 60 – and what a journey this has been! Grateful for family, friends, students, colleagues, and a scientific community that keeps me inspired. The big party? You’ll have to wait four years, when I hit my (binary) 1,000,000th birthday. 😉
3252