Sign in

Christian Wressnegger

@chwress.bsky.social
176 followers 85 following 25 posts

Professor in Computer Security at Karlsruhe Institute of Technology (KIT) intellisec.de/chris

PostsRepliesMedia
Christian Wressnegger @chwress.bsky.social · 07/07/2026
This is only one piece out of a series of cool research works @kastel-labs.bsky.social, @kitinformatik.bsky.social, and @kit.edu 🧑‍🔬 🌐 kastel-labs.de
kastel-labs.de
Home - KASTEL SRL
Explore our cybersecurity research lab, where experts innovate solutions, safeguard digital assets, and combat emerging threats. Our state-of-the-art facility drives cutting-edge research, ensuring ro...
011
Christian Wressnegger @chwress.bsky.social · 07/07/2026
Drop by our poster (#2806) on Wed, Jul 8, 2026 at 7:30 AM – 9:15 AM CEST HALL A 🌐 icml.cc/virtual/2026... See you there! 🤗
Photo of the entrance to ICML 2026Poster for the paper "Anti-Backdoor Coreset Selection via Cumulative Entropy," ICML 2026
120
Christian Wressnegger @chwress.bsky.social · 07/07/2026
Please find more details on our paper "Anti-Backdoor Coreset Selection via Cumulative Entropy" here: 💻 intellisec.de/research/abcs/ 📰 intellisec.de/pubs/2026-ic... 📑 intellisec.de/pubs/2026-ic... …and see why coreset selection makes so much more sense in this setting 😎
intellisec.de
Anti-Backdoor Coreset Selection via Cumulative Entropy
Instead of filtering poisoned samples, a more robust defense is to isolate a representative and backdoor-free dataset coreset.
120
Christian Wressnegger @chwress.bsky.social · 07/07/2026
Data poisoning is best tackled at its root, i.e., by learning a clean (backdoor-free) model despite a poisoned training data. @qzhao903.bsky.social presents a defense at ICML 2026, in which we reformulate this strategy as a coreset selection problem, giving rise to "Anti-Backdoor Coreset Selection"
Screenshot of the first page of the paper "Anti-Backdoor Coreset Selection via Cumulative Entropy," ICML 2026Schematic depiction of how the poisoned data vanishes during the training process
111
Reposted by Christian Wressnegger
KASTEL Security Research Labs @kastel-labs.bsky.social · 11/06/2026
Congratulations!👍🎉 The paper “Anti-Backdoor Coreset Selection via Cumulative Entropy” by Q. Zhao and C. Wressnegger has been accepted to ICML 2026, which will take place in Seoul from July 6–11. Congratulations to the authors on this outstanding achievement!🎆
032
Reposted by Christian Wressnegger
KIT-Fakultät für Informatik @kitinformatik.bsky.social · 06/07/2026
🏆 Forschung zur KI-Regulierung: T.-T.-Prof. Dr. iur. Frederike Zufall und Dr. iur. Gustavo Gil Gasiola wurden mit Forschern des Max-Planck-Instituts für Sicherheit und Privatsphäre mit dem CNIL/EHESS-Award 2026 ausgezeichnet. 🎉 Zum Artikel: www.informatik.kit.edu/11147_15306.... #kitinformatik
Gruppe von 5 Menschen, 3 daovn halten Pokale in den Händen Text im Bild: KIT-Forschende werden für Paper zum EU Al Act mit dem CNIL/EHESS-Preis 2026 ausgezeichnet
011
Reposted by Christian Wressnegger
Conference on Secure and Trustworthy Machine Learning @satml.org · 29/06/2026
We're pleased to announce that #SaTML2027 will be in Reykjavik, Iceland! Thanks to General Chair Giovanni Apruzzese for making the arrangements. The conference will be in early May 2027. Get your submissions ready: the deadline will be September 29, 2026. Details on the new website: satml.org
074
Reposted by Christian Wressnegger
anil oza @aniloza.bsky.social · 14/05/2026
wow — the preprint host, arxiv, is banning authors for a year if they submit papers with hallucinated citations 🤖
Twitter thread from Thomas Dietterich, reading "Attention 
@arxiv
 authors: Our Code of Conduct states that by signing your name as an author of a paper, each author takes full responsibility for all its contents, irrespective of how the contents were generated. 1/
3:03 PM · May 14, 2026
·
66.7K
 Views
Relevant
View quotes

Thomas G. Dietterich
@tdietterich
·
1h
If generative AI tools generate inappropriate language, plagiarized content, biased content, errors, mistakes, incorrect references, or misleading content, and that output is included in scientific works, it is the responsibility of the author(s). 2/
Thomas G. Dietterich
@tdietterich
·
1h
We have recently clarified our penalties for this. If a submission contains incontrovertible evidence that the authors did not check the results of LLM generation, this means we can't trust anything in the paper. 3/
Thomas G. Dietterich
@tdietterich
·
1h
The penalty is a 1-year ban from arXiv followed by the requirement that subsequent arXiv submissions must first be accepted at a reputable peer-reviewed venue. 4/
Thomas G. Dietterich
@tdietterich
·
1h
Examples of incontrovertible evidence: hallucinated references, meta-comments from the LLM ("here is a 200 word summary; would you like me to make any changes?"; "the data in this table is illustrative, fill it in with the real numbers from your experiments") end/"
9458081912
Reposted by Christian Wressnegger
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 Christian Wressnegger
Grant Sanderson @3blue1brown.com · 22/03/2026
This video was a complete joy to make. Here's a short preview, but next time you're looking to sit down for 45 minutes of math and art, take a look at the full version on YouTube: youtu.be/ldxFjLJ3rVY
626759
Reposted by Christian Wressnegger
David Buchanan @retr0.id · 13/03/2026
my "unable to decrypt message" shirt is getting a lot of confused looks at the matrix-themed party
0182
Reposted by Christian Wressnegger
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 Christian Wressnegger
Karlsruhe Institute of Technology (KIT) @kit.edu · 11/03/2026
KIT Successfully Defends Its Title as University of Excellence! “We are overjoyed,” says Professor Jan S. Hesthaven, President of KIT. www.kit.edu/kit/english/... #KITKarlsruhe #UniversityOfExcellence #ScienceForImpact #ExcellenceStrategy
Das Präsidium des KIT feiert den Erfolg in der Exzellenzstrategie.
02410
Reposted by Christian Wressnegger
Zardus @zardus.bsky.social · 13/02/2026
Hello security researchers! Like it or not, agentic AI is here. It’s time to explore its impact on novel, academic research in cybersecurity. To this end, we’re launching the Conference for Synthetic Security Research (synsec.org). Researchers, start your agents!
synsec.org
Conference of Synthetic Security Research
SynSec 2026 is an in-person conference in Phoenix focused on automated security research by AI agents, including AI-led papers and AI-first peer review.
133
Reposted by Christian Wressnegger
Kenny Paterson @kennyog.bsky.social · 11/02/2026
Almost in Karlsruhe for this talk. Looking forward to some great discussions with the KIT crypto and security community.
091
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 Christian Wressnegger
Rodger Sherman @rodger.bsky.social · 02/01/2026
went back and grabbed the full video of her intro. absolutely incredible 🇮🇹🍝👩‍🍳🤌🇮🇹🍝👩‍🍳🤌🇮🇹🍝👩‍🍳🤌🇮🇹🍝👩‍🍳🤌
5242321116
Christian Wressnegger @chwress.bsky.social · 19/12/2025
Francesco and I have a special Christmas gift for you 🎁🎅 With the help of @kastel-labs.bsky.social, we've started a new workshop on "Explainable AI and Security" co-located with EuroS&P 2026, for which we seek submissions. Details at: 🌐 xaisec-workshop.org ⏱️Deadline: Jan 29th, 2026 (AoE)
042
Reposted by Christian Wressnegger
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 Christian Wressnegger
BIFOLD Berlin Institute for the Foundations of Learning and Data @bifold.berlin · 10/11/2025
Welcome to BIFOLD. The computer scientist Prof. Dr. Christian Wressnegger from Karlsruhe Institute of Technology strengthens BIFOLD’s expertise at the intersection of AI, data management, and IT security. www.bifold.berlin/news-events/... @chwress.bsky.social @tuberlin.bsky.social @kit.edu
082
Christian Wressnegger @chwress.bsky.social · 29/10/2025
Looking forward to have @gianlucastringhini.com over at @kit.edu for our beloved distinguished lecture series 🤗 🥳
022
Christian Wressnegger @chwress.bsky.social · 20/10/2025
Please, reach out to Vera and me if you have any questions. CC: @kastel-labs.bsky.social @kitinformatik.bsky.social @kit.edu #KITKarlsruhe
kastel-labs.bsky.social
403 Forbidden
000
Christian Wressnegger @chwress.bsky.social · 20/10/2025
You prefer to organize your workshop in Europe? We've got you covered! We extended the call for workshops at EuroS&P 2026 to give you a few more days to make the move 😎 See you in Lisbon 🇵🇹 🌐 eurosp2026.ieee-security.org/cfw.ht… ⏱️ Deadline: Oct 2̶4̶t̶h̶ 30th AoE 📍Lisbon, PT
133
Reposted by Christian Wressnegger
KIT Graduate School Cyber Security @kitcybersec.bsky.social · 10/10/2025
You are an Early Career Researcher in #cybersec? Here is an opportunity: The AEC chairs of @USENIXSecurity '26 are looking for (self)nominations for the Artifact Evaluation Committee. Deadline: October 17th, 2025, so sign up soon! @chwress.bsky.social, @kumarde.bsky.social, @aurore-fass.bsky.social
059
Reposted by Christian Wressnegger
Signal @signal.org · 03/10/2025
We are alarmed by reports that Germany is on the verge of a catastrophic about-face, reversing its longstanding and principled opposition to the EU’s Chat Control proposal which, if passed, could spell the end of the right to privacy in Europe. signal.org/blog/pdfs/ge...
signal.org
4039242364
Christian Wressnegger @chwress.bsky.social · 02/10/2025
Vera Rimmer (DistriNet, KU Leuven) and I are chairing the selection. Please, reach out to us if you have any questions. CC: @kastel-labs.bsky.social @kitinformatik.bsky.social @kit.edu #KITKarlsruhe
astel-labs.bsky.social
403 Forbidden
000
Christian Wressnegger @chwress.bsky.social · 02/10/2025
The call for workshops at EuroS&P 2026 is officially open! EuroS&P is the premier, European forum for security & privacy research. The main conference is accompanied by a series of workshops. Be part of it! 😎 🌐 eurosp2026.ieee-security.org/cfw.ht… ⏱️ Deadline: Oct 24th AoE 📍Lisbon, PT
131
Reposted by Christian Wressnegger
KIT Graduate School Cyber Security @kitcybersec.bsky.social · 01/10/2025
We are expanding our social media presence! Find us on LinkedIn, Instagram @kitcybersec and Mastodon @kitcybersec@social.kit.edu. Stay tuned for regular updates on events and information on #CyberSec at #KITKarlsruhe. While you are here, have you checked out our website cybersec.kcist.kit.edu yet?
cybersec.kcist.kit.edu
KIT - KIT Graduate School Cyber Security - CyberSec - Home
012
Reposted by Christian Wressnegger
Aurore Fass @aurore-fass.bsky.social · 12/09/2025
Congratulations to USENIX Security 2025 AE: 🏆 Distinguished Artifact Awards 🏆 Distinguished Reviewer Awards ⭐ Noteworthy Reviewer Recognition 🥷 Ninja Reviewer Recognition secartifacts.github.io/usenixsec202... And thank you all for your help! CC @pvadrevu.bsky.social Tiago Heinrich
073
Christian Wressnegger @chwress.bsky.social · 27/08/2025
Max is currently in Hanoi, Vietnam and will present the paper today. Make sure not to miss it if you are at the conference. 🕚 August 27th 11:00 local time right after the break 📍 Session 2, Ballroom 2 (3/3)
000
Christian Wressnegger @chwress.bsky.social · 27/08/2025
Also this project started out as a Master's thesis @kit.edu @kitinformatik.bsky.social @kastel-labs.bsky.social Karl did an amazing job 💪 He pushed super-hard for the best possible result, which eventually was accepted at AsiaCCS 2025. Congratz again 🥳🎉 (2/3)
110
Christian Wressnegger @chwress.bsky.social · 27/08/2025
LLM-powered code assistants might suggest vulnerable code to specific user groups. Old news? Well, in contrast to prior attacks of this kind, our "Generalized Adversarial Code Suggestions" (AsiaCCS 2025) impose no restrictions on the vulnerabilities. 🌐 intellisec.de/research/adv-code (1/3)
111
Reposted by Christian Wressnegger
Mathy Vanhoef @vanhoefm.bsky.social · 12/07/2025
Yikes. Turns out you can send a plaintext radio signal to cause any train in the USA to do an emergency break. The original 'security' was just a checksum, no encryption or authentication. Reporting this took them 12 years (!) because the vendor dismissed it initially www.cisa.gov/news-events/...
cisa.gov
End-of-Train and Head-of-Train Remote Linking Protocol | CISA
1118164
Reposted by Christian Wressnegger
Clémentine Maurice @bloody-tangerine.bsky.social · 14/05/2025
Haven't seen this on Bluesky yet: S&P 2027 will take place in Montreal, Canada!
22817
Reposted by Christian Wressnegger
David D. Levine @daviddlevine.com · 12/04/2025
LLMs hallucinating nonexistent software packages with plausible names leads to a new malware vulnerability: "slopsquatting."
theregister.com
LLMs can't stop making up software dependencies and sabotaging everything
: Hallucinated package names fuel 'slopsquatting'
331337386
Reposted by Christian Wressnegger
Nicolas Papernot @nicolaspapernot.bsky.social · 05/03/2025
I will be giving a talk at the MPI-IS @maxplanckcampus.bsky.social in Tübingen next week (March 12 @ 11am). The talk will cover my group's overall approach to trust in ML, with a focus on our work on unlearning and how to obtain verifiable guarantees of trust. Details: is.mpg.de/events/speci...
174
Reposted by Christian Wressnegger
KIT Graduate School Cyber Security @kitcybersec.bsky.social · 04/03/2025
Next week Tuesday, March 11th 2025, we are going to have another Security & Privacy Lunch 🍔 We meet at 12:00 at Oxford Pub www.oxfordpub.de Everybody is welcome. See you there! 🤗
oxfordpub.de
Oxford Pub | Bier & Burger
Oxford Pub | The Finest Selection of Beer
021
Christian Wressnegger @chwress.bsky.social · 27/02/2025
💻 Code available at: github.com/two-heart/du...
github.com
GitHub - two-heart/dumpling-artifact-evaluation
Contribute to two-heart/dumpling-artifact-evaluation development by creating an account on GitHub.
010
Christian Wressnegger @chwress.bsky.social · 27/02/2025
Wow, this is massive! What started out as a Master's thesis @kit.edu @kastel-labs.bsky.social ended up with a distinguished paper award at #NDSS2025 🥳🎉 🗞️ intellisec.de/pubs/2025-nd... Congrats Liam and Julian 💪🥟, and thank you @gannimo.bsky.social and @tregua.bsky.social for the collaboration!
intellisec.de
1122
Christian Wressnegger @chwress.bsky.social · 21/02/2025
Qi is going to present our method, HARVEY, in Philadelphia at #AAAI2025 on Sunday March 2, 2pm. See you there! 😎 (5/5) 🌐 aaai.org/conference/aaai/aaai-25/pr…
aaai.org
000
Christian Wressnegger @chwress.bsky.social · 21/02/2025
In doing so, we not only excel in backdoor removal with a *worst case* remaining ASR of 0.48% (on Tiny-ImageNet with a ResNet34) but also in maintaining accuracy on the primary task of 56.65% (no defense) and 56.31% (HARVEY) *in the worst case* across different backdooring attacks. (4/5)
100
Christian Wressnegger @chwress.bsky.social · 21/02/2025
Our method refines this reference model thru a combination of splitting poisonous and benign samples, learning on poisonous and unlearning benign samples, and splitting the dataset again over multiple rounds. Eventually, we use the samples from the final split to train a perfectly benign model (3/5)
100
Christian Wressnegger @chwress.bsky.social · 21/02/2025
The idea is to remove poisonous samples that might introduce a backdoor during training. While learning a benign model is difficult in this setting, it is rather easy to learn a strongly backdoored model. This strongly backdoored model can serve as an oracle to find poisonous samples (2/5)
100
Christian Wressnegger @chwress.bsky.social · 21/02/2025
I'm happy to share that our paper "Learning the Backdoor to Remove the Backdoor" got accepted at #AAAI2025 as oral presentation (top 5%). Great job @qzhao903.bsky.social 💪 @kastel-labs.bsky.social @kit.edu (1/5) 🗞️ intellisec.de/pubs/2025-aaai.pdf 💻️ intellisec.de/research/harvey
154
Reposted by Christian Wressnegger
Laurent Cheylus @lcheylus.bsky.social · 04/02/2025
hyperfine: a command-line benchmarking Tool, written in Rust - Very useful to bench and compare performance of tools - Project by David Peter github.com/sharkdp/hyperfine
022
Reposted by Christian Wressnegger
ading.dev @ading.dev · 31/01/2025
I got Linux running in a PDF file using a RISC-V emulator. PDFs support Javascript, so Emscripten is used to compile the TinyEMU emulator to asm.js, which runs in the PDF. It boots in about 30 seconds and emulates a riscv32 buildroot system. linux.doompdf.dev/linux.pdf github.com/ading2210/li...
12311129
Reposted by Christian Wressnegger
Christian Wressnegger @chwress.bsky.social · 27/01/2025
The additional "ess" is a typo, though, and the bsky account unrelated 🫠 However, fun fact: ESS is the acronym of the underlying Helmholtz topic of our beloved KASTEL Security Research Labs -> @kastel-labs.bsky.social 😎
022
Christian Wressnegger @chwress.bsky.social · 27/01/2025
The additional "ess" is a typo, though, and the bsky account unrelated 🫠 However, fun fact: ESS is the acronym of the underlying Helmholtz topic of our beloved KASTEL Security Research Labs -> @kastel-labs.bsky.social 😎
022
Reposted by Christian Wressnegger
dmnk @dmnk.bsky.social · 18/12/2024
media.tenor.com
a penguin sitting in a field with a rainbow and the words it 's beautiful below it
ALT: a penguin sitting in a field with a rainbow and the words it 's beautiful below it
051