Seguir
Sahar Abdelnabi
Sahar Abdelnabi
AI Security Researcher, Microsoft
Dirección de correo verificada de microsoft.com - Página principal
Título
Citado por
Citado por
Año
Not what you’ve signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
S Abdelnabi*, K Greshake*, S Mishra, C Endres, T Holz, M Fritz
AISec'23 Workshop, in conjunction with CCS'23, 2023
345*2023
Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data
N Yu, V Skripniuk, S Abdelnabi, M Fritz
IEEE ICCV'21, 2021
2002021
VisualPhishNet: Zero-Day Phishing Website Detection by Visual Similarity
S Abdelnabi, K Krombholz, M Fritz
ACM CCS'20, 2020
1582020
Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding
S Abdelnabi, M Fritz
IEEE S&P'21, 2021
1272021
Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources
S Abdelnabi, R Hasan, M Fritz
35th IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021
642021
Epileptic seizure prediction using zero-crossings analysis of EEG wavelet detail coefficients
S Abdelnabi, S Eldawlatly, MI Khalil
2016 IEEE conference on computational intelligence in bioinformatics and …, 2016
542016
Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation
S Abdelnabi, A Gomaa, S Sivaprasad, L Schönherr, M Fritz
Advances in Neural Information Processing Systems (NeurIPS) - Datasets and …, 2023
26*2023
" What's in the box?!": Deflecting Adversarial Attacks by Randomly Deploying Adversarially-Disjoint Models
S Abdelnabi, M Fritz
Moving Target Defense Workshop'21, 2021
112021
Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?
E Zverev, S Abdelnabi, M Fritz, CH Lampert
arXiv preprint arXiv:2403.06833, 2024
72024
Towards high-frequency SSVEP-based target discrimination with an extended alphanumeric keyboard
S Abdelnabi, MX Huang, A Bulling
2019 IEEE International Conference on Systems, Man and Cybernetics (SMC …, 2019
72019
Fact-Saboteurs: A Taxonomy of Evidence Manipulation Attacks against Fact-Verification Systems
S Abdelnabi, M Fritz
USENIX Security Symposium'23, 2023
62023
Are you still on track!? Catching LLM Task Drift with Activations
S Abdelnabi*, A Fay*, G Cherubin, A Salem, M Fritz, A Paverd
arXiv preprint arXiv:2406.00799, 2024
32024
Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition
E Debenedetti, J Rando, D Paleka, SF Florin, D Albastroiu, N Cohen, ...
Advances in Neural Information Processing Systems (NeurIPS) - Datasets and …, 2024
2*2024
LLM Sample: part average and part ideal
S Sivaprasad, P Kaushik, S Abdelnabi, M Fritz
ICML 2024 Workshop on LLMs and Cognition, 0
2*
From Attachments to SEO: Click Here to Learn More about Clickbait PDFs!
G Stivala, S Abdelnabi, A Mengascini, M Graziano, M Fritz, G Pellegrino
Proceedings of the 39th Annual Computer Security Applications Conference, 14-28, 2023
12023
From Bad to Worse: Using Private Data to Propagate Disinformation on Online Platforms with a Greater Efficiency
PB Pranto, WH Khan, S Abdelnabi, R Weil, M Fritz, R Hasan
arXiv preprint arXiv:2306.04883, 2023
12023
Hypothesizing Missing Causal Variables with LLMs
I Sheth, S Abdelnabi, M Fritz
arXiv preprint arXiv:2409.02604, 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
R Weil, S Abdelnabi, M Fritz, R Hasan
2024 IEEE European Symposium on Security and Privacy Workshops (EuroS&PW …, 2024
2024
El sistema no puede realizar la operación en estos momentos. Inténtalo de nuevo más tarde.
Artículos 1–18