🧳 Code: github.com/mlsec-group/...
👉 Paper: mlsec.org/docs/2025-cc...
🤗 Distinguished Paper Award at CCS
with Erik Imgrund & @eisenhofer.bsky.social
4/4
🧳 Code: github.com/mlsec-group/...
👉 Paper: mlsec.org/docs/2025-cc...
🤗 Distinguished Paper Award at CCS
with Erik Imgrund & @eisenhofer.bsky.social
4/4
www.toxsec.com/p/ai-kill-ch...
www.toxsec.com/p/ai-kill-ch...
"A mechanistic view of refusal in language models" by Andy Arditi will take place on December 17th, 2025, at 5 pm CET.
Free registration at the link below:
events.teams.microsoft.com/event/9ca660...
"A mechanistic view of refusal in language models" by Andy Arditi will take place on December 17th, 2025, at 5 pm CET.
Free registration at the link below:
events.teams.microsoft.com/event/9ca660...
November 26, 17:00 - 18:00 CET.
Don't miss!
elsa-ai.eu/mlsec-semina...
November 26, 17:00 - 18:00 CET.
Don't miss!
elsa-ai.eu/mlsec-semina...
Thank you to all the young women who joined us today! Your curiosity, engagement, and enthusiasm made this day truly special.
Thank you to all the young women who joined us today! Your curiosity, engagement, and enthusiasm made this day truly special.
Authors: Erik Imgrund, Thorsten Eisenhofer, Konrad Rieck
🔗 Paper mlsec.org/docs/2025-cc...
🔗 Code github.com/mlsec-group/...
Authors: Erik Imgrund, Thorsten Eisenhofer, Konrad Rieck
🔗 Paper mlsec.org/docs/2025-cc...
🔗 Code github.com/mlsec-group/...
Erik Imgrund of the MLSEC group ( @rieck.mlsec.org ) will present the paper “Adversarial Observations in Weather Forecasting” at ACM CCS.
t1p.de/6k0uc
#MLsky #cybersecurity #ML #research #AI @tuberlin.bsky.social
Erik Imgrund of the MLSEC group ( @rieck.mlsec.org ) will present the paper “Adversarial Observations in Weather Forecasting” at ACM CCS.
t1p.de/6k0uc
#MLsky #cybersecurity #ML #research #AI @tuberlin.bsky.social
New MLSec study (BIFOLD) reveals that virtual backgrounds in video conferencing tools are not a reliable privacy shield.
t1p.de/ndqxt
#ML #Security #Cybersecurity #IT #Study @rieck.mlsec.org
New MLSec study (BIFOLD) reveals that virtual backgrounds in video conferencing tools are not a reliable privacy shield.
t1p.de/ndqxt
#ML #Security #Cybersecurity #IT #Study @rieck.mlsec.org
📜Prompt Obfuscation for Large Language Models. David Pape, Sina Mavali, Thorsten Eisenhofer, Lea Schönherr.
mlsec.org/pubs.html#pubs
📜Prompt Obfuscation for Large Language Models. David Pape, Sina Mavali, Thorsten Eisenhofer, Lea Schönherr.
mlsec.org/pubs.html#pubs
📜Seeing through: Analyzing and Attacking Virtual Backgrounds in Video Calls. Felix Weißberg, Jan-Malte Hilgefort, Steve Grogorick, Daniel Arp, Thorsten Eisenhofer, Martin Eisemann, Konrad Rieck.
mlsec.org/pubs.html#pubs
📜Seeing through: Analyzing and Attacking Virtual Backgrounds in Video Calls. Felix Weißberg, Jan-Malte Hilgefort, Steve Grogorick, Daniel Arp, Thorsten Eisenhofer, Martin Eisemann, Konrad Rieck.
mlsec.org/pubs.html#pubs
One study shows that “virtual” backgrounds in video calls can still leak real-world details — a privacy risk with broad implications.
Details: www.bifold.berlin/news-events/...
@rieck.mlsec.org @tuberlin.bsky.social
One study shows that “virtual” backgrounds in video calls can still leak real-world details — a privacy risk with broad implications.
Details: www.bifold.berlin/news-events/...
@rieck.mlsec.org @tuberlin.bsky.social
#mlsec #networksecurity #nohat2025 #cybersecurity
#mlsec #networksecurity #nohat2025 #cybersecurity