Nils Lukas - RankMe

44 papers A* 11A 2C 1Journal 29Unranked 1

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Breaking the Martingale Curse: Multi-Agent Debate via Asymmetric Cognitive Potential Energy. CoRR Yuhan Liu, Juntian Zhang, Yichen Wu, Martin Takac, Salem Lahlou, Xiuying Chen, Nils Lukas
2026	J	`jnl`	CORE: Collaborative Reasoning via Cross Teaching. CoRR Kshitij Mishra, Mirat Aubakirov, Martin Takác, Nils Lukas, Salem Lahlou
2026	J	`jnl`	Collaborative Threshold Watermarking. CoRR Tameem Bakr, Anish Ambreth, Nils Lukas
2026	J	`jnl`	Forest Before Trees: Latent Superposition for Efficient Visual Reasoning. CoRR Yubo Wang, Juntian Zhang, Yichen Wu, Yankai Lin, Nils Lukas, Yuhan Liu
2026	J	`jnl`	MAC: Multi-Agent Constitution Learning. CoRR Rushil Thareja, Gautam Gupta, Francesco Pinto, Nils Lukas
2026	J	`jnl`	RAVEN: Erasing Invisible Watermarks via Novel View Synthesis. CoRR Fahad Shamshad, Nils Lukas, Karthik Nandakumar
2026	J	`jnl`	Robust Safety Monitoring of Language Models via Activation Watermarking. CoRR Toluwani Aremu, Daniil Ognev, Samuele Poppi, Nils Lukas
2026	J	`jnl`	SD-E CoRR Kshitij Mishra, Nils Lukas, Salem Lahlou
2026	—	`conf`	SD-E2: Semantic Exploration for Reasoning Under Token Budgets. EACL (Findings) Kshitij Mishra, Nils Lukas, Salem Lahlou
2025	J	`jnl`	BURN: Backdoor Unlearning via Adversarial Boundary Analysis. CoRR Yanghao Su, Jie Zhang, Yiming Li, Tianwei Zhang, Qing Guo, Weiming Zhang, Nenghai Yu, Nils Lukas, Wenbo Zhou
2025	A*	`conf`	Cowpox: Towards the Immunity of VLM-based Multi-Agent Systems. ICML Yutong Wu, Jie Zhang, Yiming Li, Chao Zhang, Qing Guo, Han Qiu, Nils Lukas, Tianwei Zhang
2025	J	`jnl`	Cowpox: Towards the Immunity of VLM-based Multi-Agent Systems. CoRR Yutong Wu, Jie Zhang, Yiming Li, Chao Zhang, Qing Guo, Nils Lukas, Tianwei Zhang
2025	J	`jnl`	DP-Fusion: Token-Level Differentially Private Inference for Large Language Models. CoRR Rushil Thareja, Preslav Nakov, Praneeth Vepakomma, Nils Lukas
2025	J	`jnl`	First-Place Solution to NeurIPS 2024 Invisible Watermark Removal Challenge. CoRR Fahad Shamshad, Tameem Bakr, Yahia Shaaban, Noor Hussein, Karthik Nandakumar, Nils Lukas
2025	J	`jnl`	Mask Image Watermarking. CoRR Runyi Hu, Jie Zhang, Shiqian Zhao, Nils Lukas, Jiwei Li, Qing Guo, Han Qiu, Tianwei Zhang
2025	J	`jnl`	Mitigating Watermark Stealing Attacks in Generative Models via Multi-Key Watermarking. CoRR Toluwani Aremu, Noor Hussein, Munachiso Nwadike, Samuele Poppi, Jie Zhang, Karthik Nandakumar, Neil Gong, Nils Lukas
2025	A*	`conf`	Optimizing Adaptive Attacks against Watermarks for Language Models. ICML Abdulrahman Diaa, Toluwani Aremu, Nils Lukas
2025	J	`jnl`	Robust and Calibrated Detection of Authentic Multimedia Content. CoRR Sarim Hashmi, Abdelrahman Elsayed, Mohammed Talha Alam, Samuele Poppi, Nils Lukas
2025	A*	`conf`	SPIRIT: Patching Speech Language Models against Jailbreak Attacks. EMNLP Amirbek Djanibekov, Nurdaulet Mukhituly, Kentaro Inui, Hanan Aldarmaki, Nils Lukas
2025	J	`jnl`	SPIRIT: Patching Speech Language Models against Jailbreak Attacks. CoRR Amirbek Djanibekov, Nurdaulet Mukhituly, Kentaro Inui, Hanan Aldarmaki, Nils Lukas
2025	J	`jnl`	SPQR: A Standardized Benchmark for Modern Safety Alignment Methods in Text-to-Image Diffusion Models. CoRR Mohammed Talha Alam, Nada Saadi, Fahad Shamshad, Nils Lukas, Karthik Nandakumar, Fahkri Karray, Samuele Poppi
2024	A*	`conf`	Fast and Private Inference of Deep Neural Networks by Co-designing Activation Functions. USENIX Security Symposium Abdulrahman Diaa, Lucas Fenaux, Thomas Humphries, Marian Dietz, Faezeh Ebrahimianghazani, Bailey Kacsmar, Xinda Li, Nils Lukas, Rasoul Akhavan Mahdavi, Simon Oya, Ehsan Amjadian, Florian Kerschbaum
2024	A*	`conf`	Leveraging Optimization for Adaptive Attacks on Image Watermarks. ICLR Nils Lukas, Abdulrahman Diaa, Lucas Fenaux, Florian Kerschbaum
2024	J	`jnl`	Optimizing Adaptive Attacks against Content Watermarks for Language Models. CoRR Abdulrahman Diaa, Toluwani Aremu, Nils Lukas
2024	A*	`conf`	PEPSI: Practically Efficient Private Set Intersection in the Unbalanced Setting. USENIX Security Symposium Rasoul Akhavan Mahdavi, Nils Lukas, Faezeh Ebrahimianghazani, Thomas Humphries, Bailey Kacsmar, John A. Premkumar, Xinda Li, Simon Oya, Ehsan Amjadian, Florian Kerschbaum
2024	A*	`conf`	Universal Backdoor Attacks. ICLR Benjamin Schneider, Nils Lukas, Florian Kerschbaum
2023	A*	`conf`	Analyzing Leakage of Personally Identifiable Information in Language Models. SP Nils Lukas, Ahmed Salem, Robert Sim, Shruti Tople, Lukas Wutschitz, Santiago Zanella-Béguelin
2023	J	`jnl`	Analyzing Leakage of Personally Identifiable Information in Language Models. CoRR Nils Lukas, Ahmed Salem, Robert Sim, Shruti Tople, Lukas Wutschitz, Santiago Zanella-Béguelin
2023	J	`jnl`	Fast and Private Inference of Deep Neural Networks by Co-designing Activation Functions. CoRR Abdulrahman Diaa, Lucas Fenaux, Thomas Humphries, Marian Dietz, Faezeh Ebrahimianghazani, Bailey Kacsmar, Xinda Li, Nils Lukas, Rasoul Akhavan Mahdavi, Simon Oya, Ehsan Amjadian, Florian Kerschbaum
2023	J	`jnl`	Leveraging Optimization for Adaptive Attacks on Image Watermarks. CoRR Nils Lukas, Abdulrahman Diaa, Lucas Fenaux, Florian Kerschbaum
2023	J	`jnl`	PEPSI: Practically Efficient Private Set Intersection in the Unbalanced Setting. CoRR Rasoul Akhavan Mahdavi, Nils Lukas, Faezeh Ebrahimianghazani, Thomas Humphries, Bailey Kacsmar, John A. Premkumar, Xinda Li, Simon Oya, Ehsan Amjadian, Florian Kerschbaum
2023	A*	`conf`	PTW: Pivotal Tuning Watermarking for Pre-Trained Image Generators. USENIX Security Symposium Nils Lukas, Florian Kerschbaum
2023	J	`jnl`	PTW: Pivotal Tuning Watermarking for Pre-Trained Image Generators. CoRR Nils Lukas, Florian Kerschbaum
2023	J	`jnl`	Pick your Poison: Undetectability versus Robustness in Data Poisoning Attacks against Deep Image Classification. CoRR Nils Lukas, Florian Kerschbaum
2023	J	`jnl`	Privacy-Preserving Machine Learning [Cryptography]. IEEE Secur. Priv. Florian Kerschbaum, Nils Lukas
2023	J	`jnl`	Universal Backdoor Attacks. CoRR Benjamin Schneider, Nils Lukas, Florian Kerschbaum
2022	A*	`conf`	SoK: How Robust is Image Classification Deep Neural Network Watermarking? SP Nils Lukas, Edward Jiang, Xinda Li, Florian Kerschbaum
2021	A*	`conf`	Deep Neural Network Fingerprinting by Conferrable Adversarial Examples. ICLR Nils Lukas, Yuxuan Zhang, Florian Kerschbaum
2021	C	`conf`	On the Robustness of Backdoor-based Watermarking in Deep Neural Networks. IH&MMSec Masoumeh Shafieinejad, Nils Lukas, Jiaqi Wang, Xinda Li, Florian Kerschbaum
2021	J	`jnl`	SoK: How Robust is Image Classification Deep Neural Network Watermarking? (Extended Version). CoRR Nils Lukas, Edward Jiang, Xinda Li, Florian Kerschbaum
2020	A	`conf`	Differentially Private Two-Party Set Operations. EuroS&P Bailey Kacsmar, Basit Khurram, Nils Lukas, Alexander Norton, Masoumeh Shafieinejad, Zhiwei Shang, Yaser Baseri, Maryam Sepehri, Simon Oya, Florian Kerschbaum
2020	A	`conf`	Practical Over-Threshold Multi-Party Private Set Intersection. ACSAC Rasoul Akhavan Mahdavi, Thomas Humphries, Bailey Kacsmar, Simeon Krastnikov, Nils Lukas, John A. Premkumar, Masoumeh Shafieinejad, Simon Oya, Florian Kerschbaum, Erik-Oliver Blass
2019	J	`jnl`	Deep Neural Network Fingerprinting by Conferrable Adversarial Examples. CoRR Nils Lukas, Yuxuan Zhang, Florian Kerschbaum
2019	J	`jnl`	On the Robustness of the Backdoor-based Watermarking in Deep Neural Networks. CoRR Masoumeh Shafieinejad, Jiaqi Wang, Nils Lukas, Florian Kerschbaum