Abdelnabi, Sahar
- Not What You've Signed Up For: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
2023/02/23 by Kai Greshake, Sahar Abdelnabi, Greshake, Kai +9 · 10 voices · 257 citations
Computer Science · Social Sciences · #Access Control and Trust #Topic Modeling #Web Application Security Vulnerabilities #cs.AI #cs.CL #cs.CR #cs.CY
- Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data
2020/07/16 by Yu, Ning, Skripniuk, Vladislav, Abdelnabi, Sahar +1 · 20 citations
#Computer Vision and Pattern Recognition (cs.CV) #Computers and Society (cs.CY) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Graphics (cs.GR) #Machine Learning (cs.LG)
- Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding
2020/09/07 by Abdelnabi, Sahar, Fritz, Mario · 10 citations
#Computation and Language (cs.CL) #Computers and Society (cs.CY) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #I.2.7 #Machine Learning (cs.LG)
- Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation
2023/09/29 by Sahar Abdelnabi, Abdelnabi, Sahar, Amr Gomaa +7 · 15 citations
Computer Science · #Computation and Language (cs.CL) #Computers and Society (cs.CY) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Topic Modeling
- Get my drift? Catching LLM Task Drift with Activation Deltas
2024/06/02 by Abdelnabi, Sahar, Fay, Aideen, Cherubin, Giovanni +3 · 16 citations
#Computation and Language (cs.CL) #Computers and Society (cs.CY) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences
- Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?
2024/03/11 by Egor Zverev, Sahar Abdelnabi, Zverev, Egor +6 · 9 citations
Computer Science · #Mathematics, Computing, and Information Processing
- Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources
2021/11/30 by Sahar Abdelnabi, Abdelnabi, Sahar, Rakibul Hasan +3 · 3 citations
Social Sciences · Computer Science · Medicine · #Misinformation and Its Impacts #Multimodal Machine Learning Applications #Viral Infections and Outbreaks Research
- Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition
2024/06/12 by Debenedetti, Edoardo, Rando, Javier, Paleka, Daniel +18 · 5 citations
#Artificial Intelligence (cs.AI) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences
- Fact-Saboteurs: A Taxonomy of Evidence Manipulation Attacks against Fact-Verification Systems
2022/09/07 by Sahar Abdelnabi, Abdelnabi, Sahar, Mario Fritz +1 · 3 citations
Computer Science · #Adversarial Robustness in Machine Learning #Computation and Language (cs.CL) #Computers and Society (cs.CY) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Network Security and Intrusion Detection #Privacy-Preserving Technologies in Data
- Taxonomy, Opportunities, and Challenges of Representation Engineering for Large Language Models
2025/02/27 by Wehner, Jan, Abdelnabi, Sahar, Tan, Daniel +2 · 7 citations
#Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- A Theory of Response Sampling in LLMs: Part Descriptive and Part Prescriptive
2024/02/16 by Sivaprasad, Sarath, Kaushik, Pramod, Abdelnabi, Sahar +1 · 4 citations
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences
- Firewalls to Secure Dynamic LLM Agentic Networks
2025/02/03 by Sahar Abdelnabi, Abdelnabi, Sahar, Amr Gomaa +7 · 8 citations
Computer Science · Engineering · #Mobile Agent-Based Network Management #Network Security and Intrusion Detection #IPv6, Mobility, Handover, Networks, Security
- LLMail-Inject: A Dataset from a Realistic Adaptive Prompt Injection Challenge
2025/06/11 by Sahar Abdelnabi, Abdelnabi, Sahar, Aideen Fay +45 · 7 citations
Computer Science · #Security and Verification in Computing #Adversarial Robustness in Machine Learning #Advanced Malware Detection Techniques
- The Hawthorne Effect in Reasoning Models: Evaluating and Steering Test Awareness
2025/05/20 by Abdelnabi, Sahar, Salem, Ahmed · 2 citations
#Computation and Language (cs.CL) #Computers and Society (cs.CY) #FOS: Computer and information sciences
- From Bad to Worse: Using Private Data to Propagate Disinformation on Online Platforms with a Greater Efficiency
2023/06/08 by Protik Bose Pranto, Pranto, Protik Bose, Waqar Hassan Khan +9 · 1 citation
Social Sciences · #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Media Influence and Politics #Misinformation and Its Impacts #Privacy, Security, and Data Protection
- Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections
2025/10/30 by Schmotz, David, Abdelnabi, Sahar, Andriushchenko, Maksym · 1 citation
#FOS: Computer and information sciences #Machine Learning (cs.LG)
- Terrarium: Revisiting the Blackboard for Multi-Agent Safety, Privacy, and Security Studies
2025/10/16 by Nakamura, Mason, Kumar, Abhinav, Mahmud, Saaduddin +3 · 2 citations
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #I.2.11 #I.2.7