Abdelnabi, Sahar

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

Greshake, K., Abdelnabi, S., Mishra, S., Endres, C., Holz, T., & Fritz, M. (2023) · Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security

Adversarial Robustness in Machine LearningSecurity and Verification in Computing

Cited by 667

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

Yu, N., Skripniuk, V., Abdelnabi, S., & Fritz, M. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV)

Digital Media Forensic DetectionAdvanced Steganography and Watermarking Techniques

Cited by 195

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

Greshake, K., Abdelnabi, S., Mishra, S., Endres, C., Holz, T., & Fritz, M. (2023) · arXiv

Adversarial Robustness in Machine LearningSecurity and Verification in Computing

Cited by 50

Hidden in Memory: Sleeper Memory Poisoning in LLM Agents

Pulipaka, S., Hlebik, S., Raghav, L., Abdelnabi, S., Raina, V., Sheth, I., & Fritz, M. (2026) · arXiv

Adversarial Robustness in Machine LearningSecurity and Verification in Computing

Cited by 37

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

Zverev, E., Abdelnabi, S., Tabesh, S., Fritz, M., & Lampert, C. H. (2024) · arXiv

Adversarial Robustness in Machine LearningSecurity and Verification in Computing

Cited by 1

Detecting Multi-Agent Collusion Through Multi-Agent Interpretability

Rose, A., Cullen, C., Abdelnabi, S., Torr, P., Kaplowitz, B. G., & de Witt, C. S. (2026) · arXiv

Explainable Artificial Intelligence (XAI)Adversarial Robustness in Machine Learning

Cited by 0

Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks

Schmotz, D., Beurer-Kellner, L., Abdelnabi, S., & Andriushchenko, M. (2026) · arXiv

Adversarial Robustness in Machine LearningSecurity and Verification in Computing

Cited by 0

Firewalls to Secure Dynamic LLM Agentic Networks

Abdelnabi, S., Gomaa, A., Bagdasarian, E., Kristensson, P. O., & Shokri, R. (2025) · arXiv

Adversarial Robustness in Machine LearningSecurity and Verification in Computing

Cited by 0

Safety Must Precede the Deployment of Open-Ended AI

Sheth, I., Wehner, J., Abdelnabi, S., Binkyte, R., & Fritz, M. (2025) · arXiv

Ethics and Social Impacts of AISafety Systems Engineering in Autonomy

Cited by 0

SEABench: Benchmarking Endogenous Misalignment In Self-Evolving Agents

Das, S., Viswanathan, P., Donnelly, D., Huang, C., Abdelnabi, S., & Fioretto, F. (2026) · arXiv

Adversarial Robustness in Machine LearningEthics and Social Impacts of AI

Cited by 0