2 papers
cs.CR2025
ShadowLogic: Backdoors in Any Whitebox LLM
Kasimir Schulz, Amelia Kawasaki, Leo Ring
Large language models (LLMs) are widely deployed across various applications, often with safeguards to prevent the generation of harmful or restricted content. However, these safeg…
cs.CR2025
Defending Large Language Models Against Attacks With Residual Stream Activation Analysis
Amelia Kawasaki, Andrew Davis, Houssam Abbas
The widespread adoption of Large Language Models (LLMs), exemplified by OpenAI's ChatGPT, brings to the forefront the imperative to defend against adversarial threats on these mode…