Michael Backes

ORCID

Publication Activity (10 Years)

Years Active: 2002-2024
Publications (10 Years): 262

Top Venues

CoRR

CCS

USENIX Security Symposium

IACR Cryptol. ePrint Arch.

Saarland University, Saarbrücken, Germany (PHD)

Education History

Saarland University, Saarbrücken, Germany

PHD

Publications

Wai Man Si, Michael Backes, Yang Zhang
ICLGuard: Controlling In-Context Learning Behavior for Applicability Authorization. CoRR (2024)
Junjie Chu, Zeyang Sha, Michael Backes, Yang Zhang
Conversation Reconstruction Attack Against GPT Models. CoRR (2024)
Boyang Zhang, Yicong Tan, Yun Shen, Ahmed Salem, Michael Backes, Savvas Zannettou, Yang Zhang
Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification. CoRR (2024)
Yiting Qu, Zhikun Zhang, Yun Shen, Michael Backes, Yang Zhang
FAKEPCD: Fake Point Cloud Detection via Source Attribution. AsiaCCS (2024)
Minxing Zhang, Ning Yu, Rui Wen, Michael Backes, Yang Zhang
Generated Distributions Are All You Need for Membership Inference Attacks Against Generative Models. WACV (2024)
Yiting Qu, Xinyue Shen, Yixin Wu, Michael Backes, Savvas Zannettou, Yang Zhang
UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images. CoRR (2024)
Ziqing Yang, Michael Backes, Yang Zhang, Ahmed Salem
SOS! Soft Prompt Attack Against Open-Source Large Language Models. CoRR (2024)
Yiyong Liu, Rui Wen, Michael Backes, Yang Zhang
Efficient Data-Free Model Stealing with Label Diversity. CoRR (2024)
Ge Han, Ahmed Salem, Zheng Li, Shanqing Guo, Michael Backes, Yang Zhang
Detection and Attribution of Models Trained on Generated Data. ICASSP (2024)
Lichao Sun, Yue Huang, Haoran Wang, Siyuan Wu, Qihui Zhang, Chujie Gao, Yixin Huang, Wenhan Lyu, Yixuan Zhang, Xiner Li, Zhengliang Liu, Yixin Liu, Yijue Wang, Zhikun Zhang, Bhavya Kailkhura, Caiming Xiong, Chao Zhang, Chaowei Xiao, Chunyuan Li, Eric P. Xing, Furong Huang, Hao Liu, Heng Ji, Hongyi Wang, Huan Zhang, Huaxiu Yao, Manolis Kellis, Marinka Zitnik, Meng Jiang, Mohit Bansal, James Zou, Jian Pei, Jian Liu, Jianfeng Gao, Jiawei Han, Jieyu Zhao, Jiliang Tang, Jindong Wang, John Mitchell, Kai Shu, Kaidi Xu, Kai-Wei Chang, Lifang He, Lifu Huang, Michael Backes, Neil Zhenqiang Gong, Philip S. Yu, Pin-Yu Chen, Quanquan Gu, Ran Xu, Rex Ying, Shuiwang Ji, Suman Jana, Tianlong Chen, Tianming Liu, Tianyi Zhou, William Wang, Xiang Li, Xiangliang Zhang, Xiao Wang, Xing Xie, Xun Chen, Xuyu Wang, Yan Liu, Yanfang Ye, Yinzhi Cao, Yue Zhao
TrustLLM: Trustworthiness in Large Language Models. CoRR (2024)
Yixin Wu, Xinlei He, Pascal Berrang, Mathias Humbert, Michael Backes, Neil Zhenqiang Gong, Yang Zhang
Link Stealing Attacks Against Inductive Graph Neural Networks. Proc. Priv. Enhancing Technol. 2024 (4) (2024)
Xinyue Shen, Yiting Qu, Michael Backes, Yang Zhang
Prompt Stealing Attacks Against Text-to-Image Generation Models. USENIX Security Symposium (2024)
Xaver Fabian, Marco Patrignani, Marco Guarnieri, Michael Backes
Do You Even Lift? Strengthening Compiler Security Guarantees Against Spectre Attacks. CoRR (2024)
Junjie Chu, Yugeng Liu, Ziqing Yang, Xinyue Shen, Michael Backes, Yang Zhang
Comprehensive Assessment of Jailbreak Attacks Against LLMs. CoRR (2024)
Boyang Zhang, Zheng Li, Ziqing Yang, Xinlei He, Michael Backes, Mario Fritz, Yang Zhang
SecurityNet: Assessing Machine Learning Vulnerabilities on Public Models. USENIX Security Symposium (2024)
Yukun Jiang, Xinyue Shen, Rui Wen, Zeyang Sha, Junjie Chu, Yugeng Liu, Michael Backes, Yang Zhang
Games and Beyond: Analyzing the Bullet Chats of Esports Livestreaming. ICWSM (2024)
Wenhao Wang, Muhammad Ahmad Kaleem, Adam Dziedzic, Michael Backes, Nicolas Papernot, Franziska Boenisch
Memorization in Self-Supervised Learning Improves Downstream Generalization. CoRR (2024)
Yixin Wu, Xinlei He, Pascal Berrang, Mathias Humbert, Michael Backes, Neil Zhenqiang Gong, Yang Zhang
Link Stealing Attacks Against Inductive Graph Neural Networks. CoRR (2024)
Wenhao Wang, Muhammad Ahmad Kaleem, Adam Dziedzic, Michael Backes, Nicolas Papernot, Franziska Boenisch
Memorization in Self-Supervised Learning Improves Downstream Generalization. ICLR (2024)
Rui Zhang, Hongwei Li, Rui Wen, Wenbo Jiang, Yuan Zhang, Michael Backes, Yun Shen, Yang Zhang
Rapid Adoption, Hidden Risks: The Dual Impact of Large Language Model Customization. CoRR (2024)
Xinyue Shen, Yixin Wu, Michael Backes, Yang Zhang
Voice Jailbreak Attacks Against GPT-4o. CoRR (2024)
Yixin Wu, Rui Wen, Michael Backes, Pascal Berrang, Mathias Humbert, Yun Shen, Yang Zhang
Quantifying Privacy Risks of Prompts in Visual Prompt Learning. USENIX Security Symposium (2024)
Rui Zhang, Hongwei Li, Rui Wen, Wenbo Jiang, Yuan Zhang, Michael Backes, Yun Shen, Yang Zhang
Instruction Backdoor Attacks Against Customized LLMs. USENIX Security Symposium (2024)
Rui Wen, Zhengyu Zhao, Zhuoran Liu, Michael Backes, Tianhao Wang, Yang Zhang
Is Adversarial Training Really a Silver Bullet for Mitigating Data Poisoning? ICLR (2023)
Yiting Qu, Xinlei He, Shannon Pierson, Michael Backes, Yang Zhang, Savvas Zannettou
On the Evolution of (Hateful) Memes by Means of Multimodal Contrastive Learning. SP (2023)
Giorgio Di Tizio, Patrick Speicher, Milivoj Simeonovski, Michael Backes, Ben Stock, Robert Künnemann
Pareto-optimal Defenses for the Web Infrastructure: Theory and Practice. ACM Trans. Priv. Secur. 26 (2) (2023)
Yihan Ma, Zhengyu Zhao, Xinlei He, Zheng Li, Michael Backes, Yang Zhang
Generative Watermarking Against Unauthorized Subject-Driven Image Synthesis. CoRR (2023)
Min Chen, Zhikun Zhang, Tianhao Wang, Michael Backes, Yang Zhang
FACE-AUDITOR: Data Auditing in Facial Recognition Systems. CoRR (2023)
Hai Huang, Zhengyu Zhao, Michael Backes, Yun Shen, Yang Zhang
Prompt Backdoors in Visual Prompt Learning. CoRR (2023)
Yugeng Liu, Zheng Li, Michael Backes, Yun Shen, Yang Zhang
Backdoor Attacks Against Dataset Distillation. CoRR (2023)
Minxing Zhang, Ning Yu, Rui Wen, Michael Backes, Yang Zhang
Generated Distributions Are All You Need for Membership Inference Attacks Against Generative Models. CoRR (2023)
Yiyong Liu, Michael Backes, Xiao Zhang
Transferable Availability Poisoning Attacks. CoRR (2023)
Matthis Kruse, Michael Backes, Marco Patrignani
Secure Composition of Robust and Optimising Compilers. CoRR (2023)
Minxing Zhang, Michael Backes, Xiao Zhang
Generating Less Certain Adversarial Examples Improves Robust Generalization. CoRR (2023)
Yiting Qu, Xinyue Shen, Xinlei He, Michael Backes, Savvas Zannettou, Yang Zhang
Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models. CoRR (2023)
Cristian-Alexandru Staicu, Sazzadur Rahaman, Ágnes Kiss, Michael Backes
Bilingual Problems: Studying the Security Risks Incurred by Native Extensions in Scripting Languages. USENIX Security Symposium (2023)
Xinlei He, Xinyue Shen, Zeyuan Chen, Michael Backes, Yang Zhang
MGTBench: Benchmarking Machine-Generated Text Detection. CoRR (2023)
Bartlomiej Surma, Tahleen A. Rahman, Monique M. B. Breteler, Michael Backes, Yang Zhang
You Are How You Walk: Quantifying Privacy Risks in Step Count Data. CoRR (2023)
Boyang Zhang, Zheng Li, Ziqing Yang, Xinlei He, Michael Backes, Mario Fritz, Yang Zhang
SecurityNet: Assessing Machine Learning Vulnerabilities on Public Models. CoRR (2023)
Yixin Wu, Ning Yu, Michael Backes, Yun Shen, Yang Zhang
On the Proactive Generation of Unsafe Images From Text-To-Image Models Using Benign Prompts. CoRR (2023)
Zheng Li, Ning Yu, Ahmed Salem, Michael Backes, Mario Fritz, Yang Zhang
UnGANable: Defending Against GAN-based Face Manipulation. USENIX Security Symposium (2023)
Haiming Wang, Zhikun Zhang, Tianhao Wang, Shibo He, Michael Backes, Jiming Chen, Yang Zhang
PrivTrace: Differentially Private Trajectory Synthesis by Adaptive Markov Models. USENIX Security Symposium (2023)
Yihan Ma, Zhikun Zhang, Ning Yu, Xinlei He, Michael Backes, Yun Shen, Yang Zhang
Generated Graph Detection. CoRR (2023)
Peihua Ma, Yixin Wu, Ning Yu, Yang Zhang, Michael Backes, Qin Wang, Cheng-I Wei
Vision-language models boost food composition compilation. CoRR (2023)
Michael Thomas Smith, Kathrin Grosse, Michael Backes, Mauricio A. Álvarez
Adversarial vulnerability bounds for Gaussian process classification. Mach. Learn. 112 (3) (2023)
Xinyue Shen, Zeyuan Chen, Michael Backes, Yun Shen, Yang Zhang
"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models. CoRR (2023)
Yiting Qu, Xinyue Shen, Xinlei He, Michael Backes, Savvas Zannettou, Yang Zhang
Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models. CCS (2023)
Yixin Wu, Rui Wen, Michael Backes, Pascal Berrang, Mathias Humbert, Yun Shen, Yang Zhang
Quantifying Privacy Risks of Prompts in Visual Prompt Learning. CoRR (2023)
Min Chen, Zhikun Zhang, Tianhao Wang, Michael Backes, Yang Zhang
FACE-AUDITOR: Data Auditing in Facial Recognition Systems. USENIX Security Symposium (2023)
Hamed Rasifard, Rahul Gopinath, Michael Backes, Hamed Nemati
SEAL: Capability-Based Access Control for Data-Analytic Scenarios. SACMAT (2023)
Hai Huang, Zhengyu Zhao, Michael Backes, Yun Shen, Yang Zhang
Composite Backdoor Attacks Against Large Language Models. CoRR (2023)
Yiting Qu, Zhikun Zhang, Yun Shen, Michael Backes, Yang Zhang
FAKEPCD: Fake Point Cloud Detection via Source Attribution. CoRR (2023)
Zeyang Sha, Xinlei He, Ning Yu, Michael Backes, Yang Zhang
Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders. CVPR (2023)
Yihan Ma, Zhikun Zhang, Ning Yu, Xinlei He, Michael Backes, Yun Shen, Yang Zhang
Generated Graph Detection. ICML (2023)
Yugeng Liu, Zheng Li, Michael Backes, Yun Shen, Yang Zhang
Backdoor Attacks Against Dataset Distillation. NDSS (2023)
Ziqing Yang, Zeyang Sha, Michael Backes, Yang Zhang
From Visual Prompt Learning to Zero-Shot Transfer: Mapping Is All You Need. CoRR (2023)
Wai Man Si, Michael Backes, Yang Zhang
Mondrian: Prompt Abstraction Attack Against Large Language Models for Cheaper API Pricing. CoRR (2023)
Xinyue Shen, Yiting Qu, Michael Backes, Yang Zhang
Prompt Stealing Attacks Against Text-to-Image Generation Models. CoRR (2023)
Rui Wen, Tianhao Wang, Michael Backes, Yang Zhang, Ahmed Salem
Last One Standing: A Comparative Analysis of Security and Privacy of Soft Prompt Tuning, LoRA, and In-Context Learning. CoRR (2023)
Wai Man Si, Michael Backes, Yang Zhang, Ahmed Salem
Two-in-One: A Model Hijacking Attack Against Text Generation Models. CoRR (2023)
Xinyue Shen, Zeyuan Chen, Michael Backes, Yang Zhang
In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPT. CoRR (2023)
Wai Man Si, Michael Backes, Yang Zhang, Ahmed Salem
Two-in-One: A Model Hijacking Attack Against Text Generation Models. USENIX Security Symposium (2023)
Boyang Zhang, Xinyue Shen, Wai Man Si, Zeyang Sha, Zeyuan Chen, Ahmed Salem, Yun Shen, Michael Backes, Yang Zhang
Comprehensive Assessment of Toxicity in ChatGPT. CoRR (2023)
Yuan Xin, Michael Backes, Xiao Zhang
Provably Robust Cost-Sensitive Learning via Randomized Smoothing. CoRR (2023)
Yugeng Liu, Zheng Li, Michael Backes, Yun Shen, Yang Zhang
Watermarking Diffusion Model. CoRR (2023)
Sanam Ghorbani Lyastani, Michael Backes, Sven Bugiel
A Systematic Study of the Consistency of Two-Factor Authentication User Journeys on Top-Ranked Websites. NDSS (2023)
Yugeng Liu, Tianshuo Cong, Zhengyu Zhao, Michael Backes, Yun Shen, Yang Zhang
Robustness Over Time: Understanding Adversarial Examples' Effectiveness on Longitudinal Versions of Large Language Models. CoRR (2023)
Zhengyu Zhao, Hanwei Zhang, Renjue Li, Ronan Sicre, Laurent Amsaleg, Michael Backes, Qi Li, Chao Shen
Revisiting Transferable Adversarial Image Examples: Attack Categorization, Evaluation Guidelines, and New Insights. CoRR (2023)
Ziqing Yang, Xinlei He, Zheng Li, Michael Backes, Mathias Humbert, Pascal Berrang, Yang Zhang
Data Poisoning Attacks Against Multimodal Encoders. ICML (2023)
Ahmed Salem, Rui Wen, Michael Backes, Shiqing Ma, Yang Zhang
Dynamic Backdoor Attacks Against Machine Learning Models. EuroS&P (2022)
Yiyong Liu, Zhengyu Zhao, Michael Backes, Yang Zhang
Membership Inference Attacks by Exploiting Loss Trajectory. CCS (2022)
Xinyue Shen, Xinlei He, Michael Backes, Jeremy Blackburn, Savvas Zannettou, Yang Zhang
On Xing Tian and the Perseverance of Anti-China Sentiment Online. CoRR (2022)
Sanam Ghorbani Lyastani, Michael Backes, Sven Bugiel
A Systematic Study of the Consistency of Two-Factor Authentication User Journeys on Top-Ranked Websites (Extended Version). CoRR (2022)
Yixin Wu, Ning Yu, Zheng Li, Michael Backes, Yang Zhang
Membership Inference Attacks Against Text-to-image Generation Models. CoRR (2022)
Zhikun Zhang, Min Chen, Michael Backes, Yun Shen, Yang Zhang
Inference Attacks Against Graph Neural Networks. USENIX Security Symposium (2022)
Yugeng Liu, Rui Wen, Xinlei He, Ahmed Salem, Zhikun Zhang, Michael Backes, Emiliano De Cristofaro, Mario Fritz, Yang Zhang
ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models. USENIX Security Symposium (2022)
Wai Man Si, Michael Backes, Jeremy Blackburn, Emiliano De Cristofaro, Gianluca Stringhini, Savvas Zannettou, Yang Zhang
Why So Toxic? Measuring and Triggering Toxic Behavior in Open-Domain Chatbots. CoRR (2022)
Zhengyu Zhao, Hanwei Zhang, Renjue Li, Ronan Sicre, Laurent Amsaleg, Michael Backes
Towards Good Practices in Evaluating Transfer Adversarial Attacks. CoRR (2022)
Hai Huang, Zhikun Zhang, Yun Shen, Michael Backes, Qi Li, Yang Zhang
On the Privacy Risks of Cell-Based NAS Architectures. CCS (2022)
Yiyong Liu, Zhengyu Zhao, Michael Backes, Yang Zhang
Membership Inference Attacks by Exploiting Loss Trajectory. CoRR (2022)
Xinyue Shen, Xinlei He, Zheng Li, Yun Shen, Michael Backes, Yang Zhang
Backdoor Attacks in the Supply Chain of Masked Image Modeling. CoRR (2022)
Yiting Qu, Xinlei He, Shannon Pierson, Michael Backes, Yang Zhang, Savvas Zannettou
On the Evolution of (Hateful) Memes by Means of Multimodal Contrastive Learning. CoRR (2022)
Yun Shen, Yufei Han, Zhikun Zhang, Min Chen, Ting Yu, Michael Backes, Yang Zhang, Gianluca Stringhini
Finding MNEMON: Reviving Memories of Node Embeddings. CoRR (2022)
Zheng Li, Yiyong Liu, Xinlei He, Ning Yu, Michael Backes, Yang Zhang
Auditing Membership Leakages of Multi-Exit Networks. CCS (2022)
Haiming Wang, Zhikun Zhang, Tianhao Wang, Shibo He, Michael Backes, Jiming Chen, Yang Zhang
PrivTrace: Differentially Private Trajectory Synthesis by Adaptive Markov Model. CoRR (2022)
Ziqing Yang, Xinlei He, Zheng Li, Michael Backes, Mathias Humbert, Pascal Berrang, Yang Zhang
Data Poisoning Attacks Against Multimodal Encoders. CoRR (2022)
Wai Man Si, Michael Backes, Jeremy Blackburn, Emiliano De Cristofaro, Gianluca Stringhini, Savvas Zannettou, Yang Zhang
Why So Toxic?: Measuring and Triggering Toxic Behavior in Open-Domain Chatbots. CCS (2022)
Michael Backes, Pascal Berrang, Lucjan Hanzlik, Ivan Pryvalov
A Framework for Constructing Single Secret Leader Election from MPC. ESORICS (2) (2022)
Yun Shen, Yufei Han, Zhikun Zhang, Min Chen, Ting Yu, Michael Backes, Yang Zhang, Gianluca Stringhini
Finding MNEMON: Reviving Memories of Node Embeddings. CCS (2022)
Lukas Bieringer, Kathrin Grosse, Michael Backes, Battista Biggio, Katharina Krombholz
Industrial practitioners' mental models of adversarial machine learning. SOUPS @ USENIX Security Symposium (2022)
Xinyue Shen, Xinlei He, Michael Backes, Jeremy Blackburn, Savvas Zannettou, Yang Zhang
On Xing Tian and the Perseverance of Anti-China Sentiment Online. ICWSM (2022)
Zeyang Sha, Xinlei He, Ning Yu, Michael Backes, Yang Zhang
Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders. CoRR (2022)
Zheng Li, Yiyong Liu, Xinlei He, Ning Yu, Michael Backes, Yang Zhang
Auditing Membership Leakages of Multi-Exit Networks. CoRR (2022)
Hai Huang, Zhikun Zhang, Yun Shen, Michael Backes, Qi Li, Yang Zhang
On the Privacy Risks of Cell-Based NAS Architectures. CoRR (2022)
Ahmed Salem, Michael Backes, Yang Zhang
Get a Model! Model Hijacking Attack Against Machine Learning Models. NDSS (2022)
Trung Tin Nguyen, Michael Backes, Ben Stock
Freely Given Consent?: Studying Consent Notice of Third-Party Tracking and Its Violations of GDPR in Android Apps. CCS (2022)
Min Chen, Zhikun Zhang, Tianhao Wang, Michael Backes, Mathias Humbert, Yang Zhang
Graph Unlearning. CCS (2022)
Zheng Li, Ning Yu, Ahmed Salem, Michael Backes, Mario Fritz, Yang Zhang
UnGANable: Defending Against GAN-based Face Manipulation. CoRR (2022)
Michael Backes, Pascal Berrang, Lucjan Hanzlik, Ivan Pryvalov
A framework for constructing Single Secret Leader Election from MPC. IACR Cryptol. ePrint Arch. 2022 (2022)
Kathrin Grosse, Taesung Lee, Battista Biggio, Youngja Park, Michael Backes, Ian M. Molloy
Backdoor smoothing: Demystifying backdoor attacks on deep neural networks. Comput. Secur. 120 (2022)

Michael Backes.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Michael Backes