activity
20192025
most cited"What's in the box?!": Deflecting Adversarial Attacks by Randomly Deploying Adversarially-Disjoint Models

1 citations · 1 across the 3 of their papers we have counts for

collaborators

7 papers

cs.CR2025

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

Sahar Abdelnabi, Aideen Fay, Ahmed Salem +22

Indirect Prompt Injection attacks exploit the inherent limitation of Large Language Models (LLMs) to distinguish between instructions and data in their inputs. Despite numerous def…

cs.CL2025

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

Sahar Abdelnabi, Ahmed Salem

Reasoning-focused LLMs sometimes alter their behavior when they detect that they are being evaluated, which can lead them to optimize for test-passing performance or to comply more…

cs.LG2025

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

Jan Wehner, Sahar Abdelnabi, Daniel Tan +2

Representation Engineering (RepE) is a novel paradigm for controlling the behavior of LLMs. Unlike traditional approaches that modify inputs or fine-tune the model, RepE directly m…

cs.LG2024

Context-Aware Reasoning On Parametric Knowledge for Inferring Causal Variables

Ivaxi Sheth, Sahar Abdelnabi, Mario Fritz

Scientific discovery catalyzes human intellectual advances, driven by the cycle of hypothesis generation, experimental design, evaluation, and assumption refinement. Central to thi…

cs.LG20211 cited

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

Sahar Abdelnabi, Mario Fritz

Machine learning models are now widely deployed in real-world applications. However, the existence of adversarial examples has been long considered a real threat to such models. Wh…

cs.CR2020

Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding

Sahar Abdelnabi, Mario Fritz

Recent advances in natural language generation have introduced powerful language models with high-quality output text. However, this raises concerns about the potential misuse of s…