Sahar Abdelnabi

According to our database, Sahar Abdelnabi authored at least 46 papers between 2019 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Models That Know How Evaluations Are Designed Score Safer.

Katharina Deckenbach, Haritz Puerto, Jonas Geiping, Sahar Abdelnabi

CoRR, May, 2026

Decomposing and Measuring Evaluation Awareness.

Changling Li, Terry Jingchen Zhang, Jie Zhang, Zhijing Jin, Sahar Abdelnabi, Maksym Andriushchenko

CoRR, May, 2026

Measuring Security Without Fooling Ourselves: Why Benchmarking Agents Is Hard.

Sahar Abdelnabi, Chris Hicks, Konrad Rieck, Ahmad-Reza Sadeghi

CoRR, May, 2026

AI Agents May Always Fall for Prompt Injections.

Sahar Abdelnabi, Eugene Bagdasarian

CoRR, May, 2026

Hidden in Memory: Sleeper Memory Poisoning in LLM Agents.

Sidharth Pulipaka, Stanislau Hlebik, Leonidas Raghav, Sahar Abdelnabi, Vyas Raina, Ivaxi Sheth, Mario Fritz

CoRR, May, 2026

No More, No Less: Task Alignment in Terminal Agents.

Sina Mavali, David Pape, Jonathan Evertz, Samira Abedini, Devansh Srivastav, Thorsten Eisenhofer, Sahar Abdelnabi, Lea Schönherr

CoRR, May, 2026

Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks.

David Schmotz, Luca Beurer-Kellner, Sahar Abdelnabi, Maksym Andriushchenko

CoRR, February, 2026

Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems.

Mason Nakamura, Abhinav Kumar, Saswat Das, Sahar Abdelnabi, Saaduddin Mahmud, Ferdinando Fioretto, Shlomo Zilberstein, Eugene Bagdasarian

CoRR, February, 2026

Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs.

Ahmed Salem, Andrew Paverd, Sahar Abdelnabi

CoRR, February, 2026

ConVerse: Benchmarking Contextual Safety in Agent-to-Agent Conversations.

Amr Gomaa, Ahmed Salem, Sahar Abdelnabi

Proceedings of the Findings of the Association for Computational Linguistics: EACL 2026, 2026

2025

Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections.

David Schmotz, Sahar Abdelnabi, Maksym Andriushchenko

CoRR, October, 2025

Terrarium: Revisiting the Blackboard for Multi-Agent Safety, Privacy, and Security Studies.

Mason Nakamura, Abhinav Kumar, Saaduddin Mahmud, Sahar Abdelnabi, Shlomo Zilberstein, Eugene Bagdasarian

CoRR, October, 2025

LLMail-Inject: A Dataset from a Realistic Adaptive Prompt Injection Challenge.

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

CoRR, June, 2025

Linear Control of Test Awareness Reveals Differential Compliance in Reasoning Models.

Sahar Abdelnabi, Ahmed Salem

CoRR, May, 2025

Safety is Essential for Responsible Open-Ended Systems.

Ivaxi Sheth, Jan Wehner, Sahar Abdelnabi, Ruta Binkyte, Mario Fritz

CoRR, February, 2025

Firewalls to Secure Dynamic LLM Agentic Networks.

Sahar Abdelnabi, Amr Gomaa, Eugene Bagdasarian, Per Ola Kristensson, Reza Shokri

CoRR, February, 2025

Taxonomy, Opportunities, and Challenges of Representation Engineering for Large Language Models.

Jan Wehner, Sahar Abdelnabi, Daniel Tan, David Krueger, Mario Fritz

Trans. Mach. Learn. Res., 2025

Get My Drift? Catching LLM Task Drift with Activation Deltas.

Sahar Abdelnabi, Aideen Fay, Giovanni Cherubin, Ahmed Salem, Mario Fritz, Andrew Paverd

Proceedings of the IEEE Conference on Secure and Trustworthy Machine Learning, 2025

Contextual Integrity in LLMs via Reasoning and Reinforcement Learning.

Guangchen Lan, Huseyin A. Inan, Sahar Abdelnabi, Janardhan Kulkarni, Lukas Wutschitz, Reza Shokri, Christopher Brinton, Robert Sim

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

The Hawthorne Effect in Reasoning Models: Evaluating and Steering Test Awareness.

Sahar Abdelnabi, Ahmed Salem

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?

Egor Zverev, Sahar Abdelnabi, Soroush Tabesh, Mario Fritz, Christoph H. Lampert

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Context-Aware Reasoning On Parametric Knowledge for Inferring Causal Variables.

Ivaxi Sheth, Sahar Abdelnabi, Mario Fritz

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

A Theory of Response Sampling in LLMs: Part Descriptive and Part Prescriptive.

Sarath Sivaprasad, Pramod Kaushik, Sahar Abdelnabi, Mario Fritz

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

2024

On the opportunities and risks of machine learning to online and societal safety.

Sahar Abdelnabi

PhD thesis, 2024

Hypothesizing Missing Causal Variables with LLMs.

Ivaxi Sheth, Sahar Abdelnabi, Mario Fritz

CoRR, 2024

Are you still on track!? Catching LLM Task Drift with Activations.

Sahar Abdelnabi, Aideen Fay, Giovanni Cherubin, Ahmed Salem, Mario Fritz, Andrew Paverd

CoRR, 2024

Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?

Egor Zverev, Sahar Abdelnabi, Mario Fritz, Christoph H. Lampert

CoRR, 2024

Exploring Value Biases: How LLMs Deviate Towards the Ideal.

Sarath Sivaprasad, Pramod Kaushik, Sahar Abdelnabi, Mario Fritz

CoRR, 2024

Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition.

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

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation.

Sahar Abdelnabi, Amr Gomaa, Sarath Sivaprasad, Lea Schönherr, Mario Fritz

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Tell Me What You Like and I Know What You Will Share: Topical Interest Influences Behavior Toward News From High and Low Credible Sources.

Rebecca Weil, Sahar Abdelnabi, Mario Fritz, Rakibul Hasan

Proceedings of the IEEE European Symposium on Security and Privacy Workshops, 2024

2023

LLM-Deliberation: Evaluating LLMs with Interactive Multi-Agent Negotiation Games.

Sahar Abdelnabi, Amr Gomaa, Sarath Sivaprasad, Lea Schönherr, Mario Fritz

CoRR, 2023

A Large-Scale Study of Phishing PDF Documents.

Giada Stivala, Sahar Abdelnabi, Andrea Mengascini, Mariano Graziano, Mario Fritz, Giancarlo Pellegrino

CoRR, 2023

From Bad to Worse: Using Private Data to Propagate Disinformation on Online Platforms with a Greater Efficiency.

Protik Bose Pranto, Waqar Hassan Khan, Sahar Abdelnabi, Rebecca Weil, Mario Fritz, Rakibul Hasan

CoRR, 2023

More than you've asked for: A Comprehensive Analysis of Novel Prompt Injection Threats to Application-Integrated Large Language Models.

Kai Greshake, Sahar Abdelnabi, Shailesh Mishra, Christoph Endres, Thorsten Holz, Mario Fritz

CoRR, 2023

Fact-Saboteurs: A Taxonomy of Evidence Manipulation Attacks against Fact-Verification Systems.

Sahar Abdelnabi, Mario Fritz

Proceedings of the 32nd USENIX Security Symposium, 2023

Not What You've Signed Up For: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection.

Sahar Abdelnabi, Kai Greshake, Shailesh Mishra, Christoph Endres, Thorsten Holz, Mario Fritz

Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security, 2023

From Attachments to SEO: Click Here to Learn More about Clickbait PDFs!

Giada Stivala, Sahar Abdelnabi, Andrea Mengascini, Mariano Graziano, Mario Fritz, Giancarlo Pellegrino

Proceedings of the Annual Computer Security Applications Conference, 2023

2022

Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources.

Sahar Abdelnabi, Rakibul Hasan, Mario Fritz

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2021

Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding.

Sahar Abdelnabi, Mario Fritz

Proceedings of the 42nd IEEE Symposium on Security and Privacy, 2021

Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data.

Ning Yu, Vladislav Skripniuk, Sahar Abdelnabi, Mario Fritz

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

What's in the box: Deflecting Adversarial Attacks by Randomly Deploying Adversarially-Disjoint Models.

Sahar Abdelnabi, Mario Fritz

Proceedings of the MTD@CCS 2021: Proceedings of the 8th ACM Workshop on Moving Target Defense, 2021

2020

Black-Box Watermarking for Generative Adversarial Networks.

Vladislav Skripniuk, Ning Yu, Sahar Abdelnabi, Mario Fritz

CoRR, 2020

VisualPhishNet: Zero-Day Phishing Website Detection by Visual Similarity.

Sahar Abdelnabi, Katharina Krombholz, Mario Fritz

Proceedings of the CCS '20: 2020 ACM SIGSAC Conference on Computer and Communications Security, 2020

2019

WhiteNet: Phishing Website Detection by Visual Whitelists.

Sahar Abdelnabi, Katharina Krombholz, Mario Fritz

CoRR, 2019

Towards High-Frequency SSVEP-Based Target Discrimination with an Extended Alphanumeric Keyboard.

Sahar Abdelnabi, Michael Xuelin Huang, Andreas Bulling

Proceedings of the 2019 IEEE International Conference on Systems, Man and Cybernetics, 2019