Lea Schönherr

55 papers A* 12A 5B 2Journal 31Unranked 4

Year	Rank	Type	Title / Venue / Authors
2026	A*	`conf`	"That's another doom I haven't thought about": A User Study on AI Labels as a Safeguard Against Image-Based Misinformation. CHI Sandra Höltervennhoff, Jonas Ricker, Maike M. Raphael, Charlotte Schwedes, Rebecca Weil, Asja Fischer, Thorsten Holz, Lea Schönherr, Sascha Fahl
2026	J	`jnl`	Buffer-free class-incremental learning with out-of-distribution detection. Pattern Recognit. Srishti Gupta, Daniele Angioni, Maura Pintor, Ambra Demontis, Lea Schönherr, Fabio Roli, Battista Biggio
2026	J	`jnl`	Don't Trust Stubborn Neighbors: A Security Framework for Agentic Networks. CoRR Samira Abedini, Sina Mavali, Lea Schönherr, Martin Pawelczyk, Rebekka Burkholz
2026	J	`jnl`	Evaluation of Audio Language Models for Fairness, Safety, and Security. CoRR Ranya Aloufi, Srishti Gupta, Soumya Shaw, Battista Biggio, Lea Schönherr
2026	J	`jnl`	Unknown Unknowns: Why Hidden Intentions in LLMs Evade Detection. CoRR Devansh Srivastav, David Pape, Lea Schönherr
2025	J	`jnl`	Are Modern Speech Enhancement Systems Vulnerable to Adversarial Attacks? CoRR Rostislav Makarov, Lea Schönherr, Timo Gerkmann
2025	J	`jnl`	Buffer-free Class-Incremental Learning with Out-of-Distribution Detection. CoRR Srishti Gupta, Daniele Angioni, Maura Pintor, Ambra Demontis, Lea Schönherr, Battista Biggio, Fabio Roli
2025	J	`jnl`	Chasing Shadows: Pitfalls in LLM Security Research. CoRR Jonathan Evertz, Niklas Risse, Nicolai Neuer, Andreas Müller, Philipp Normann, Gaetano Sapia, Srishti Gupta, David Pape, Soumya Shaw, Devansh Srivastav, Christian Wressnegger, Erwin Quiring, Thorsten Eisenhofer, Daniel Arp, Lea Schönherr
2025	A	`conf`	Code Generation of Smart Contracts with LLMs: A Case Study on Hyperledger Fabric. ISSRE Luca Olivieri, David Beste, Luca Negrini, Lea Schönherr, Antonio Emanuele Cinà, Pietro Ferrara
2025	—	`conf`	Exploring the Potential of LLMs for Code Deobfuscation. DIMVA (1) David Beste, Grégoire Menguy, Hossein Hajipour, Mario Fritz, Antonio Emanuele Cinà, Sébastien Bardin, Thorsten Holz, Thorsten Eisenhofer, Lea Schönherr
2025	A*	`conf`	Prompt Obfuscation for Large Language Models. USENIX Security Symposium David Pape, Sina Mavali, Thorsten Eisenhofer, Lea Schönherr
2025	J	`jnl`	Rethinking Robustness in Machine Learning: A Posterior Agreement Approach. CoRR João B. S. Carvalho, Alessandro Torcinovich, Victor Jimenez Rodriguez, Antonio Emanuele Cinà, Carlos Cotrini, Lea Schönherr, Joachim M. Buhmann
2025	J	`jnl`	Rethinking Robustness in Machine Learning: A Posterior Agreement Approach. Trans. Mach. Learn. Res. João B. S. Carvalho, Victor Jimenez Rodriguez, Alessandro Torcinovich, Antonio Emanuele Cinà, Carlos Cotrini, Lea Schönherr, Joachim M. Buhmann
2025	J	`jnl`	Security Benefits and Side Effects of Labeling AI-Generated Images. CoRR Sandra Höltervennhoff, Jonas Ricker, Maike M. Raphael, Charlotte Schwedes, Rebecca Weil, Asja Fischer, Thorsten Holz, Lea Schönherr, Sascha Fahl
2025	A*	`conf`	σ-zero: Gradient-based Optimization of ℓ0-norm Adversarial Examples. ICLR Antonio Emanuele Cinà, Francesco Villani, Maura Pintor, Lea Schönherr, Battista Biggio, Marcello Pelillo
2024	A*	`conf`	A Representative Study on Human Detection of Artificially Generated Media Across Countries. SP Joel Frank, Franziska Herbert, Jonas Ricker, Lea Schönherr, Thorsten Eisenhofer, Asja Fischer, Markus Dürmuth, Thorsten Holz
2024	—	`conf`	CodeLMSec Benchmark: Systematically Evaluating and Finding Security Vulnerabilities in Black-Box Code Language Models. SaTML Hossein Hajipour, Keno Hassler, Thorsten Holz, Lea Schönherr, Mario Fritz
2024	A*	`conf`	Conning the Crypto Conman: End-to-End Analysis of Cryptocurrency-based Technical Support Scams. SP Bhupendra Acharya, Muhammad Saad, Antonio Emanuele Cinà, Lea Schönherr, Hoang Dai Nguyen, Adam Oest, Phani Vadrevu, Thorsten Holz
2024	J	`jnl`	Conning the Crypto Conman: End-to-End Analysis of Cryptocurrency-based Technical Support Scams. CoRR Bhupendra Acharya, Muhammad Saad, Antonio Emanuele Cinà, Lea Schönherr, Hoang Dai Nguyen, Adam Oest, Phani Vadrevu, Thorsten Holz
2024	A*	`conf`	Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation. NeurIPS Sahar Abdelnabi, Amr Gomaa, Sarath Sivaprasad, Lea Schönherr, Mario Fritz
2024	A*	`conf`	Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition. NeurIPS Edoardo Debenedetti, Javier Rando, Daniel Paleka, Silaghi Fineas Florin, Dragos Albastroiu, Niv Cohen, Yuval Lemberg, Reshmi Ghosh, Rui Wen, Ahmed Salem, Giovanni Cherubin, Santiago Zanella-Béguelin, Robin Schmid, Victor Klemm, Takahiro Miki, Chenhao Li, Stefan Kraft, Mario Fritz, Florian Tramèr, Sahar Abdelnabi, Lea Schönherr
2024	J	`jnl`	Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition. CoRR Edoardo Debenedetti, Javier Rando, Daniel Paleka, Silaghi Fineas Florin, Dragos Albastroiu, Niv Cohen, Yuval Lemberg, Reshmi Ghosh, Rui Wen, Ahmed Salem, Giovanni Cherubin, Santiago Zanella-Béguelin, Robin Schmid, Victor Klemm, Takahiro Miki, Chenhao Li, Stefan Kraft, Mario Fritz, Florian Tramèr, Sahar Abdelnabi, Lea Schönherr
2024	J	`jnl`	Fake It Until You Break It: On the Adversarial Robustness of AI-generated Image Detectors. CoRR Sina Mavali, Jonas Ricker, David Pape, Yash Sharma, Asja Fischer, Lea Schönherr
2024	J	`jnl`	HexaCoder: Secure Code Generation via Oracle-Guided Synthetic Training Data. CoRR Hossein Hajipour, Lea Schönherr, Thorsten Holz, Mario Fritz
2024	J	`jnl`	Prompt Obfuscation for Large Language Models. CoRR David Pape, Thorsten Eisenhofer, Lea Schönherr
2024	J	`jnl`	Rag and Roll: An End-to-End Evaluation of Indirect Prompt Manipulations in LLM-based Application Frameworks. CoRR Gianluca De Stefano, Lea Schönherr, Giancarlo Pellegrino
2024	A*	`conf`	The Imitation Game: Exploring Brand Impersonation Attacks on Social Media Platforms. USENIX Security Symposium Bhupendra Acharya, Dario Lazzaro, Efrén López-Morales, Adam Oest, Muhammad Saad, Antonio Emanuele Cinà, Lea Schönherr, Thorsten Holz
2024	J	`jnl`	Whispers in the Machine: Confidentiality in LLM-integrated Systems. CoRR Jonathan Evertz, Merlin Chlosta, Lea Schönherr, Thorsten Eisenhofer
2024	J	`jnl`	σ-zero: Gradient-based Optimization of 𝓁 CoRR Antonio Emanuele Cinà, Francesco Villani, Maura Pintor, Lea Schönherr, Battista Biggio, Marcello Pelillo
2023	J	`jnl`	A Representative Study on Human Detection of Artificially Generated Media Across Countries. CoRR Joel Frank, Franziska Herbert, Jonas Ricker, Lea Schönherr, Thorsten Eisenhofer, Asja Fischer, Markus Dürmuth, Thorsten Holz
2023	A*	`conf`	Drone Security and the Mysterious Case of DJI's DroneID. NDSS Nico Schiller, Merlin Chlosta, Moritz Schloegel, Nils Bars, Thorsten Eisenhofer, Tobias Scharnowski, Felix Domke, Lea Schönherr, Thorsten Holz
2023	J	`jnl`	LLM-Deliberation: Evaluating LLMs with Interactive Multi-Agent Negotiation Games. CoRR Sahar Abdelnabi, Amr Gomaa, Sarath Sivaprasad, Lea Schönherr, Mario Fritz
2023	B	`conf`	On the Limitations of Model Stealing with Uncertainty Quantification Models. ESANN David Pape, Sina Däubener, Thorsten Eisenhofer, Antonio Emanuele Cinà, Lea Schönherr
2023	J	`jnl`	On the Limitations of Model Stealing with Uncertainty Quantification Models. CoRR David Pape, Sina Däubener, Thorsten Eisenhofer, Antonio Emanuele Cinà, Lea Schönherr
2023	J	`jnl`	Systematically Finding Security Vulnerabilities in Black-Box Code Generation Models. CoRR Hossein Hajipour, Thorsten Holz, Lea Schönherr, Mario Fritz
2023	—	`conf`	Venomave: Targeted Poisoning Against Speech Recognition. SaTML Hojjat Aghakhani, Lea Schönherr, Thorsten Eisenhofer, Dorothea Kolossa, Thorsten Holz, Christopher Kruegel, Giovanni Vigna
2022	A	`conf`	Clustering-based Wake Word Detection in Privacy-aware Acoustic Sensor Networks. INTERSPEECH Timm Koppelmann, Luca Becker, Alexandru Nelus, Rene Glitza, Lea Schönherr, Rainer Martin
2022	J	`jnl`	Exploring accidental triggers of smart speakers. Comput. Speech Lang. Lea Schönherr, Maximilian Golla, Thorsten Eisenhofer, Jan Wiele, Dorothea Kolossa, Thorsten Holz
2021	—	`—`	Adversarially robust speech and speaker recognition. Lea Schönherr
2021	A*	`conf`	Dompteur: Taming Audio Adversarial Examples. USENIX Security Symposium Thorsten Eisenhofer, Lea Schönherr, Joel Frank, Lars Speckemeier, Dorothea Kolossa, Thorsten Holz
2021	J	`jnl`	Dompteur: Taming Audio Adversarial Examples. CoRR Thorsten Eisenhofer, Lea Schönherr, Joel Frank, Lars Speckemeier, Dorothea Kolossa, Thorsten Holz
2021	A	`conf`	Privacy-Preserving Feature Extraction for Cloud-Based Wake Word Verification. Interspeech Timm Koppelmann, Alexandru Nelus, Lea Schönherr, Dorothea Kolossa, Rainer Martin
2021	—	`conf`	WaveFake: A Data Set to Facilitate Audio Deepfake Detection. NeurIPS Datasets and Benchmarks Joel Frank, Lea Schönherr
2021	J	`jnl`	WaveFake: A Data Set to Facilitate Audio Deepfake Detection. CoRR Joel Frank, Lea Schönherr
2020	A	`conf`	Detecting Adversarial Examples for Speech Recognition via Uncertainty Quantification. INTERSPEECH Sina Däubener, Lea Schönherr, Asja Fischer, Dorothea Kolossa
2020	J	`jnl`	Detecting Adversarial Examples for Speech Recognition via Uncertainty Quantification. CoRR Sina Däubener, Lea Schönherr, Asja Fischer, Dorothea Kolossa
2020	A	`conf`	Imperio: Robust Over-the-Air Adversarial Examples for Automatic Speech Recognition Systems. ACSAC Lea Schönherr, Thorsten Eisenhofer, Steffen Zeiler, Thorsten Holz, Dorothea Kolossa
2020	A*	`conf`	Leveraging Frequency Analysis for Deep Fake Image Recognition. ICML Joel Frank, Thorsten Eisenhofer, Lea Schönherr, Asja Fischer, Dorothea Kolossa, Thorsten Holz
2020	J	`jnl`	Leveraging Frequency Analysis for Deep Fake Image Recognition. CoRR Joel Frank, Thorsten Eisenhofer, Lea Schönherr, Asja Fischer, Dorothea Kolossa, Thorsten Holz
2020	B	`conf`	Loss Functions for Deep Monaural Speech Enhancement. IJCNN Jan Freiwald, Lea Schönherr, Christopher Schymura, Steffen Zeiler, Dorothea Kolossa
2020	J	`jnl`	Unacceptable, where is my privacy? Exploring Accidental Triggers of Smart Speakers. CoRR Lea Schönherr, Maximilian Golla, Thorsten Eisenhofer, Jan Wiele, Dorothea Kolossa, Thorsten Holz
2020	J	`jnl`	VENOMAVE: Clean-Label Poisoning Against Speech Recognition. CoRR Hojjat Aghakhani, Thorsten Eisenhofer, Lea Schönherr, Dorothea Kolossa, Thorsten Holz, Christopher Kruegel, Giovanni Vigna
2019	A*	`conf`	Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hiding. NDSS Lea Schönherr, Katharina Kohls, Steffen Zeiler, Thorsten Holz, Dorothea Kolossa
2019	J	`jnl`	Robust Over-the-Air Adversarial Examples Against Automatic Speech Recognition Systems. CoRR Lea Schönherr, Steffen Zeiler, Thorsten Holz, Dorothea Kolossa
2018	J	`jnl`	Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hiding. CoRR Lea Schönherr, Katharina Kohls, Steffen Zeiler, Thorsten Holz, Dorothea Kolossa