Sahar Abdelnabi

45 papers A* 8A 1B 1Journal 28Unranked 7

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems. CoRR Mason Nakamura, Abhinav Kumar, Saswat Das, Sahar Abdelnabi, Saaduddin Mahmud, Ferdinando Fioretto, Shlomo Zilberstein, Eugene Bagdasarian
2026	—	`conf`	ConVerse: Benchmarking Contextual Safety in Agent-to-Agent Conversations. EACL (Findings) Amr Gomaa, Ahmed Salem, Sahar Abdelnabi
2026	J	`jnl`	Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks. CoRR David Schmotz, Luca Beurer-Kellner, Sahar Abdelnabi, Maksym Andriushchenko
2026	J	`jnl`	Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs. CoRR Ahmed Salem, Andrew Paverd, Sahar Abdelnabi
2025	—	`conf`	A Theory of Response Sampling in LLMs: Part Descriptive and Part Prescriptive. ACL (1) Sarath Sivaprasad, Pramod Kaushik, Sahar Abdelnabi, Mario Fritz
2025	J	`jnl`	Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections. CoRR David Schmotz, Sahar Abdelnabi, Maksym Andriushchenko
2025	A*	`conf`	Can LLMs Separate Instructions From Data? And What Do We Even Mean By That? ICLR Egor Zverev, Sahar Abdelnabi, Soroush Tabesh, Mario Fritz, Christoph H. Lampert
2025	J	`jnl`	ConVerse: Benchmarking Contextual Safety in Agent-to-Agent Conversations. CoRR Amr Gomaa, Ahmed Salem, Sahar Abdelnabi
2025	—	`conf`	Context-Aware Reasoning On Parametric Knowledge for Inferring Causal Variables. EMNLP (Findings) Ivaxi Sheth, Sahar Abdelnabi, Mario Fritz
2025	J	`jnl`	Contextual Integrity in LLMs via Reasoning and Reinforcement Learning. CoRR Guangchen Lan, Huseyin A. Inan, Sahar Abdelnabi, Janardhan Kulkarni, Lukas Wutschitz, Reza Shokri, Christopher G. Brinton, Robert Sim
2025	J	`jnl`	Firewalls to Secure Dynamic LLM Agentic Networks. CoRR Sahar Abdelnabi, Amr Gomaa, Eugene Bagdasarian, Per Ola Kristensson, Reza Shokri
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	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`	Safety is Essential for Responsible Open-Ended Systems. CoRR Ivaxi Sheth, Jan Wehner, Sahar Abdelnabi, Ruta Binkyte, Mario Fritz
2025	J	`jnl`	Taxonomy, Opportunities, and Challenges of Representation Engineering for Large Language Models. CoRR Jan Wehner, Sahar Abdelnabi, Daniel Tan, David Krueger, Mario Fritz
2025	J	`jnl`	Taxonomy, Opportunities, and Challenges of Representation Engineering for Large Language Models. Trans. Mach. Learn. Res. Jan Wehner, Sahar Abdelnabi, Daniel Tan, David Krueger, Mario Fritz
2025	J	`jnl`	Terrarium: Revisiting the Blackboard for Multi-Agent Safety, Privacy, and Security Studies. CoRR Mason Nakamura, Abhinav Kumar, Saaduddin Mahmud, Sahar Abdelnabi, Shlomo Zilberstein, Eugene Bagdasarian
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`	Can LLMs Separate Instructions From Data? And What Do We Even Mean By That? CoRR Egor Zverev, Sahar Abdelnabi, Mario Fritz, Christoph H. Lampert
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`	Exploring Value Biases: How LLMs Deviate Towards the Ideal. CoRR Sarath Sivaprasad, Pramod Kaushik, Sahar Abdelnabi, Mario Fritz
2024	J	`jnl`	Hypothesizing Missing Causal Variables with LLMs. CoRR Ivaxi Sheth, Sahar Abdelnabi, Mario Fritz
2024	—	`conf`	Tell Me What You Like and I Know What You Will Share: Topical Interest Influences Behavior Toward News From High and Low Credible Sources. EuroS&P Workshops Rebecca Weil, Sahar Abdelnabi, Mario Fritz, Rakibul Hasan
2023	J	`jnl`	A Large-Scale Study of Phishing PDF Documents. CoRR Giada Stivala, Sahar Abdelnabi, Andrea Mengascini, Mariano Graziano, Mario Fritz, Giancarlo Pellegrino
2023	A*	`conf`	Fact-Saboteurs: A Taxonomy of Evidence Manipulation Attacks against Fact-Verification Systems. USENIX Security Symposium Sahar Abdelnabi, Mario Fritz
2023	A	`conf`	From Attachments to SEO: Click Here to Learn More about Clickbait PDFs! ACSAC Giada Stivala, Sahar Abdelnabi, Andrea Mengascini, Mariano Graziano, Mario Fritz, Giancarlo Pellegrino
2023	J	`jnl`	From Bad to Worse: Using Private Data to Propagate Disinformation on Online Platforms with a Greater Efficiency. CoRR Protik Bose Pranto, Waqar Hassan Khan, Sahar Abdelnabi, Rebecca Weil, Mario Fritz, Rakibul Hasan
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	J	`jnl`	More than you've asked for: A Comprehensive Analysis of Novel Prompt Injection Threats to Application-Integrated Large Language Models. CoRR Kai Greshake, Sahar Abdelnabi, Shailesh Mishra, Christoph Endres, Thorsten Holz, Mario Fritz
2023	—	`conf`	Not What You've Signed Up For: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection. AISec@CCS Sahar Abdelnabi, Kai Greshake, Shailesh Mishra, Christoph Endres, Thorsten Holz, Mario Fritz
2022	J	`jnl`	Fact-Saboteurs: A Taxonomy of Evidence Manipulation Attacks against Fact-Verification Systems. CoRR Sahar Abdelnabi, Mario Fritz
2022	A*	`conf`	Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources. CVPR Sahar Abdelnabi, Rakibul Hasan, Mario Fritz
2021	J	`jnl`	"What's in the box?!": Deflecting Adversarial Attacks by Randomly Deploying Adversarially-Disjoint Models. CoRR Sahar Abdelnabi, Mario Fritz
2021	A*	`conf`	Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding. SP Sahar Abdelnabi, Mario Fritz
2021	A*	`conf`	Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data. ICCV Ning Yu, Vladislav Skripniuk, Sahar Abdelnabi, Mario Fritz
2021	J	`jnl`	Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources. CoRR Sahar Abdelnabi, Rakibul Hasan, Mario Fritz
2021	—	`conf`	What's in the box: Deflecting Adversarial Attacks by Randomly Deploying Adversarially-Disjoint Models. MTD@CCS Sahar Abdelnabi, Mario Fritz
2020	J	`jnl`	Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding. CoRR Sahar Abdelnabi, Mario Fritz
2020	J	`jnl`	Black-Box Watermarking for Generative Adversarial Networks. CoRR Vladislav Skripniuk, Ning Yu, Sahar Abdelnabi, Mario Fritz
2020	A*	`conf`	VisualPhishNet: Zero-Day Phishing Website Detection by Visual Similarity. CCS Sahar Abdelnabi, Katharina Krombholz, Mario Fritz
2019	B	`conf`	Towards High-Frequency SSVEP-Based Target Discrimination with an Extended Alphanumeric Keyboard. SMC Sahar Abdelnabi, Michael Xuelin Huang, Andreas Bulling
2019	J	`jnl`	WhiteNet: Phishing Website Detection by Visual Whitelists. CoRR Sahar Abdelnabi, Katharina Krombholz, Mario Fritz