Lea Schönherr
@leaschnherr
Followers
352
Following
216
Media
14
Statuses
120
Tenure-track faculty @CISPA, working on ML and computer security.
Joined December 2011
RT @ho_hajipour: 8/8 🔗 The paper is available at: Our code, fine-tuned models, and synthesized data will be availa….
github.com
Contribute to hexacoder-ai/hexacoder development by creating an account on GitHub.
0
3
0
It was an honor to be invited. I really enjoyed giving this talk at AISec.
Happening right now:.AISec invited talk by @leaschnherr (@CISPA). Title: Challenges and Threats in Generative AI: Misuse and Exploits
1
0
9
RT @javirandor: ⭐️ NeurIPS D&B Spotlight ⭐️. We will be presenting the findings from our LLM CTF together with a multi-turn prompt extracti….
0
6
0
RT @sahar_abdelnabi: Happy to share that our paper was (finally!!) accepted at #NeurIPS2024 D&B!!. We propose dynamic, multi-agent, scorabl….
0
6
0
Wie leicht erkennst du generierte Medien? Wir haben dazu einige Beispiele auf Instagram geteilt @CISPA . Hier noch mit (echtem) Bild von Behind-the-scenes 📹
0
0
1
I am delighted to be giving a talk on the risks (and chances) of generative AI as part of the HIDA Lecture Series on July 25th. It's online, so come and join us : ).
Join us for an engaging lecture in which @leaschnherr will explore real-world examples of AI misuse. Don't miss this opportunity to deepen your understanding of AI security. Register now: .📅 Date: June 27, 2024.🕒Time: 3:00 PM CEST.📍 Online.
0
0
1
RT @javirandor: The report and dataset from our LLM CTF are finally out! Learn more about the winning strategies and the resulting dataset!….
0
8
0
RT @piraxtor: (1/5) Super excited that I will be presenting Conning the Crypto Conman: End-to-End Analysis of Cryptocurrency-based Technica….
0
5
0
RT @ho_hajipour: 1/4📢 Excited to announce our presentation at @satml_conf on "CodeLMSec Benchmark: Systematically Evaluating & Finding Secu….
0
3
0
RT @edoardo_debe: The @satml_conf LLM CTF has come to an end!. 🥇Huge congrats to the defender winning team Hestia (@NivCohenHuji @Yuvlem) w….
0
20
0
A Representative Study on Human Detection of Artificially Generated Media Across Countries (n=3,002) covering audio, image, and text 🥳. Our #SP24 @IEEESSP paper is now available Together with @joool_f @FranziskaPiaH @thorstenholz @jonasricker @_thrsten
0
9
28
Good luck and a lot of fun for every team! . The defense phase is open until January 15. For more details:
Our @satml_conf LLM Capture-the-flag is now live!.Can you find successful defenses and attacks for prompt injection?.
0
0
1
RT @AbdelnabiSahar: How well can LLMs perform in multi-agent negotiation? How can we develop new benchmarks that measure interactive tasks?….
0
11
0
Congratulations! And I hope that we can continue our collaboration now and in the future 🥳. It is like always a pleasure!.
Excited to announce my new role as an Assistant Professor (RTD-A) at the @UniGenova! 🎉. There will be much to explore in the coming years, particularly in the area of Trustworthy #AI and #ML for industries and security applications. 🤖💡. #AcademicLife #MachineLearning #Genoa.
1
1
8
Ich habe in den letzten TL;DR über Gefahren und Risiken von Large Language Models gesprochen. Danke für die Einladung. Es hat sehr spaß gemacht 😄.
0
0
7
happy to have you here 😄.
@CISPA @adversarial_ML @trustworthy_ml @xwasco Big thanks to @leaschnherr for this prestigious opportunity to work with her at CISPA. Very grateful to everyone who has been part of this journey and, in particular, to my supervisor @PelilloMarcello , co-supervisor @biggiobattista, and mentor @ambrademontis.
0
0
7