Ahmed Salem - RankMe

62 papers A* 13A 3Misc 1Journal 41Unranked 3

Year	Rank	Type	Title / Venue / Authors
2026	—	`conf`	ConVerse: Benchmarking Contextual Safety in Agent-to-Agent Conversations. EACL (Findings) Amr Gomaa, Ahmed Salem, Sahar Abdelnabi
2026	J	`jnl`	GRP-Obliteration: Unaligning LLMs With a Single Unlabeled Prompt. CoRR Mark Russinovich, Yanan Cai, Keegan Hines, Giorgio Severi, Blake Bullwinkel, Ahmed Salem
2026	J	`jnl`	Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs. CoRR Ahmed Salem, Andrew Paverd, Sahar Abdelnabi
2025	J	`jnl`	A Representation Engineering Perspective on the Effectiveness of Multi-Turn Jailbreaks. CoRR Blake Bullwinkel, Mark Russinovich, Ahmed Salem, Santiago Zanella-Béguelin, Daniel Jones, Giorgio Severi, Eugenia Kim, Keegan Hines, Amanda J. Minnich, Yonatan Zunger, Ram Shankar Siva Kumar
2025	A*	`conf`	Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification. EMNLP Boyang Zhang, Yicong Tan, Yun Shen, Ahmed Salem, Michael Backes, Savvas Zannettou, Yang Zhang
2025	J	`jnl`	ConVerse: Benchmarking Contextual Safety in Agent-to-Agent Conversations. CoRR Amr Gomaa, Ahmed Salem, Sahar Abdelnabi
2025	—	`conf`	Get My Drift? Catching LLM Task Drift with Activation Deltas. SaTML Sahar Abdelnabi, Aideen Fay, Giovanni Cherubin, Ahmed Salem, Mario Fritz, Andrew Paverd
2025	A*	`conf`	Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack. USENIX Security Symposium Mark Russinovich, Ahmed Salem, Ronen Eldan
2025	J	`jnl`	Jailbreaking is (Mostly) Simpler Than You Think. CoRR Mark Russinovich, Ahmed Salem
2025	J	`jnl`	LLMail-Inject: A Dataset from a Realistic Adaptive Prompt Injection Challenge. CoRR Sahar Abdelnabi, Aideen Fay, Ahmed Salem, Egor Zverev, Kai-Chieh Liao, Chi-Huang Liu, Chun-Chih Kuo, Jannis Weigend, Danyael Manlangit, Alex Apostolov, Haris Umair, João Donato, Masayuki Kawakita, Athar Mahboob, Tran Huu Bach, Tsun-Han Chiang, Myeongjin Cho, Hajin Choi, Byeonghyeon Kim, Hyeonjin Lee, Benjamin Pannell, Conor McCauley, Mark Russinovich, Andrew Paverd, Giovanni Cherubin
2025	J	`jnl`	Linear Control of Test Awareness Reveals Differential Compliance in Reasoning Models. CoRR Sahar Abdelnabi, Ahmed Salem
2025	J	`jnl`	LogiPlan: A Structured Benchmark for Logical Planning and Relational Reasoning in LLMs. CoRR Yanan Cai, Ahmed Salem, Besmira Nushi, Mark Russinovich
2025	A	`conf`	Neeko: Model Hijacking Attacks Against Generative Adversarial Networks. ICME Junjie Chu, Yugeng Liu, Xinlei He, Michael Backes, Yang Zhang, Ahmed Salem
2025	J	`jnl`	Obliviate: Efficient Unmemorization for Protecting Intellectual Property in Large Language Models. CoRR Mark Russinovich, Ahmed Salem
2025	J	`jnl`	Permissive Information-Flow Analysis for Large Language Models. Trans. Mach. Learn. Res. Shoaib Ahmed Siddiqui, Radhika Gaonkar, Boris Köpf, David Krueger, Andrew Paverd, Ahmed Salem, Shruti Tople, Lukas Wutschitz, Menglin Xia, Santiago Zanella-Béguelin
2025	J	`jnl`	Securing AI Agents with Information-Flow Control. CoRR Manuel Costa, Boris Köpf, Aashish Kolluri, Andrew Paverd, Mark Russinovich, Ahmed Salem, Shruti Tople, Lukas Wutschitz, Santiago Zanella-Béguelin
2025	J	`jnl`	The Price of Intelligence. Commun. ACM Mark Russinovich, Ahmed Salem, Santiago Zanella-Béguelin, Yonatan Zunger
2024	J	`jnl`	Are you still on track!? Catching LLM Task Drift with Activations. CoRR Sahar Abdelnabi, Aideen Fay, Giovanni Cherubin, Ahmed Salem, Mario Fritz, Andrew Paverd
2024	J	`jnl`	Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification. CoRR Boyang Zhang, Yicong Tan, Yun Shen, Ahmed Salem, Michael Backes, Savvas Zannettou, Yang Zhang
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	Misc	`conf`	Detection and Attribution of Models Trained on Generated Data. ICASSP Ge Han, Ahmed Salem, Zheng Li, Shanqing Guo, Michael Backes, Yang Zhang
2024	J	`jnl`	Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack. CoRR Mark Russinovich, Ahmed Salem, Ronen Eldan
2024	J	`jnl`	Hey, That's My Model! Introducing Chain & Hash, An LLM Fingerprinting Technique. CoRR Mark Russinovich, Ahmed Salem
2024	J	`jnl`	Permissive Information-Flow Analysis for Large Language Models. CoRR Shoaib Ahmed Siddiqui, Radhika Gaonkar, Boris Köpf, David Krueger, Andrew Paverd, Ahmed Salem, Shruti Tople, Lukas Wutschitz, Menglin Xia, Santiago Zanella-Béguelin
2024	J	`jnl`	SOS! Soft Prompt Attack Against Open-Source Large Language Models. CoRR Ziqing Yang, Michael Backes, Yang Zhang, Ahmed Salem
2024	J	`jnl`	The Price of Intelligence: Three risks inherent in LLMs. ACM Queue Mark Russinovich, Ahmed Salem, Santiago Zanella-Béguelin, Yonatan Zunger
2024	J	`jnl`	Vera Verto: Multimodal Hijacking Attack. CoRR Minxing Zhang, Ahmed Salem, Michael Backes, Yang Zhang
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	A*	`conf`	Bayesian Estimation of Differential Privacy. ICML Santiago Zanella-Béguelin, Lukas Wutschitz, Shruti Tople, Ahmed Salem, Victor Rühle, Andrew Paverd, Mohammad Naseri, Boris Köpf, Daniel Jones
2023	J	`jnl`	Comprehensive Assessment of Toxicity in ChatGPT. CoRR Boyang Zhang, Xinyue Shen, Wai Man Si, Zeyang Sha, Zeyuan Chen, Ahmed Salem, Yun Shen, Michael Backes, Yang Zhang
2023	J	`jnl`	Last One Standing: A Comparative Analysis of Security and Privacy of Soft Prompt Tuning, LoRA, and In-Context Learning. CoRR Rui Wen, Tianhao Wang, Michael Backes, Yang Zhang, Ahmed Salem
2023	J	`jnl`	Maatphor: Automated Variant Analysis for Prompt Injection Attacks. CoRR Ahmed Salem, Andrew Paverd, Boris Köpf
2023	J	`jnl`	Rethinking Privacy in Machine Learning Pipelines from an Information Flow Control Perspective. CoRR Lukas Wutschitz, Boris Köpf, Andrew Paverd, Saravan Rajmohan, Ahmed Salem, Shruti Tople, Santiago Zanella-Béguelin, Menglin Xia, Victor Rühle
2023	A*	`conf`	SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning. SP Ahmed Salem, Giovanni Cherubin, David Evans, Boris Köpf, Andrew Paverd, Anshuman Suri, Shruti Tople, Santiago Zanella-Béguelin
2023	A*	`conf`	Two-in-One: A Model Hijacking Attack Against Text Generation Models. USENIX Security Symposium Wai Man Si, Michael Backes, Yang Zhang, Ahmed Salem
2023	J	`jnl`	Two-in-One: A Model Hijacking Attack Against Text Generation Models. CoRR Wai Man Si, Michael Backes, Yang Zhang, Ahmed Salem
2023	A*	`conf`	UnGANable: Defending Against GAN-based Face Manipulation. USENIX Security Symposium Zheng Li, Ning Yu, Ahmed Salem, Michael Backes, Mario Fritz, Yang Zhang
2022	—	`—`	Adversarial inference and manipulation of machine learning models. Ahmed Salem
2022	J	`jnl`	Bayesian Estimation of Differential Privacy. CoRR Santiago Zanella-Béguelin, Lukas Wutschitz, Shruti Tople, Ahmed Salem, Victor Rühle, Andrew Paverd, Mohammad Naseri, Boris Köpf, Daniel Jones
2022	A	`conf`	Dynamic Backdoor Attacks Against Machine Learning Models. EuroS&P Ahmed Salem, Rui Wen, Michael Backes, Shiqing Ma, Yang Zhang
2022	A*	`conf`	Get a Model! Model Hijacking Attack Against Machine Learning Models. NDSS Ahmed Salem, Michael Backes, Yang Zhang
2022	A*	`conf`	ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models. USENIX Security Symposium Yugeng Liu, Rui Wen, Xinlei He, Ahmed Salem, Zhikun Zhang, Michael Backes, Emiliano De Cristofaro, Mario Fritz, Yang Zhang
2022	J	`jnl`	SoK: Let The Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning. CoRR Ahmed Salem, Giovanni Cherubin, David Evans, Boris Köpf, Andrew Paverd, Anshuman Suri, Shruti Tople, Santiago Zanella-Béguelin
2022	J	`jnl`	UnGANable: Defending Against GAN-based Face Manipulation. CoRR Zheng Li, Ning Yu, Ahmed Salem, Michael Backes, Mario Fritz, Yang Zhang
2021	A	`conf`	BadNL: Backdoor Attacks against NLP Models with Semantic-preserving Improvements. ACSAC Xiaoyi Chen, Ahmed Salem, Dingfan Chen, Michael Backes, Shiqing Ma, Qingni Shen, Zhonghai Wu, Yang Zhang
2021	J	`jnl`	Get a Model! Model Hijacking Attack Against Machine Learning Models. CoRR Ahmed Salem, Michael Backes, Yang Zhang
2021	J	`jnl`	ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models. CoRR Yugeng Liu, Rui Wen, Xinlei He, Ahmed Salem, Zhikun Zhang, Michael Backes, Emiliano De Cristofaro, Mario Fritz, Yang Zhang
2021	—	`conf`	MLCapsule: Guarded Offline Deployment of Machine Learning as a Service. CVPR Workshops Lucjan Hanzlik, Yang Zhang, Kathrin Grosse, Ahmed Salem, Maximilian Augustin, Michael Backes, Mario Fritz
2020	J	`jnl`	BAAAN: Backdoor Attacks Against Autoencoder and GAN-Based Machine Learning Models. CoRR Ahmed Salem, Yannick Sautter, Michael Backes, Mathias Humbert, Yang Zhang
2020	J	`jnl`	BadNL: Backdoor Attacks Against NLP Models. CoRR Xiaoyi Chen, Ahmed Salem, Michael Backes, Shiqing Ma, Yang Zhang
2020	J	`jnl`	Don't Trigger Me! A Triggerless Backdoor Attack Against Deep Neural Networks. CoRR Ahmed Salem, Michael Backes, Yang Zhang
2020	J	`jnl`	Dynamic Backdoor Attacks Against Machine Learning Models. CoRR Ahmed Salem, Rui Wen, Michael Backes, Shiqing Ma, Yang Zhang
2020	A*	`conf`	Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning. USENIX Security Symposium Ahmed Salem, Apratim Bhattacharya, Michael Backes, Mario Fritz, Yang Zhang
2019	A*	`conf`	ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models. NDSS Ahmed Salem, Yang Zhang, Mathias Humbert, Pascal Berrang, Mario Fritz, Michael Backes
2019	A*	`conf`	MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples. CCS Jinyuan Jia, Ahmed Salem, Michael Backes, Yang Zhang, Neil Zhenqiang Gong
2019	J	`jnl`	MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples. CoRR Jinyuan Jia, Ahmed Salem, Michael Backes, Yang Zhang, Neil Zhenqiang Gong
2019	J	`jnl`	Privacy-Preserving Similar Patient Queries for Combined Biomedical Data. Proc. Priv. Enhancing Technol. Ahmed Salem, Pascal Berrang, Mathias Humbert, Michael Backes
2019	J	`jnl`	Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning. CoRR Ahmed Salem, Apratim Bhattacharyya, Michael Backes, Mario Fritz, Yang Zhang
2018	J	`jnl`	ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models. CoRR Ahmed Salem, Yang Zhang, Mathias Humbert, Mario Fritz, Michael Backes
2018	J	`jnl`	MLCapsule: Guarded Offline Deployment of Machine Learning as a Service. CoRR Lucjan Hanzlik, Yang Zhang, Kathrin Grosse, Ahmed Salem, Max Augustin, Michael Backes, Mario Fritz