Skip to content
View SerenaGW's full-sized avatar
👩‍💻
Check the new version of my last report!
👩‍💻
Check the new version of my last report!

Block or report SerenaGW

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
SerenaGW/README.md

Hi 👋

I'm an AI security researcher, focusing on cutting-edge vulnerabilities that challenge the internal logic of language models.


My Mission!

I research novel phenomena and advanced Red Teaming techniques at the LLM frontier to understand the fundamental aspects and internal mechanisms of models, generating verifiable safety and systemic security.


🛠️ Projects and Contributions

  • Architectural Collapse via Blank Spaces Language (BSL) An Exploratory Research on Low-Entropy Whitespace Attacks in Large Language Models

https://github.com/SerenaGW/RedTeamLowEnthropy

  • The Paradox of Optimized Fragility: The Modulation of Reasoning in LLMs This repository addresses a fundamental question: Can an In-Context Learning (ICL) guide change the way a Large Language Model reasons? This research explores an innovative finding about LLMs: ICL guides are not just passive examples, but heuristic shortcuts that alter the models' internal logic.

https://github.com/SerenaGW/LLMLanguageFineTuningModifiesMathLogic

  • The Future of AI Safety: How Symbolic Language Reveals Paths Towards LLM Resilience: This repository showcases research into novel adversarial techniques for Large Language Models (LLMs), focusing on the use of a unique symbolic language combined with social engineering to identify and exploit alignment vulnerabilities, impacting AI safety and trustworthiness. This research also provides a fine-tuning guide as a prototype for both adversarial mitigation and logical comprehension.

https://github.com/SerenaGW/LLMReadteamSymbolic

  • Semantic Re-signification and Linguistic Denial of Service in LLMs: This repository presents the findings of a novel AI Red Teaming research focused on "Semantic Re-signification," a technique designed to explore vulnerabilities in Large Language Models (LLMs) by manipulating their fundamental semantic understanding.

https://github.com/SerenaGW/LLMReadTeamLinguisticDoS/tree/main


📧 Contact

https://www.linkedin.com/in/serena-gw/

image

Pinned Loading

  1. LLMLanguageFineTuningModifiesMathLogic LLMLanguageFineTuningModifiesMathLogic Public

    This repository showcases research into the fundamental impact of low-cost in-context learning on the internal logic of Large Language Models (LLMs). By using different ICL guides

    1

  2. LLMReadteamSymbolic LLMReadteamSymbolic Public

    This repository showcases research into novel adversarial techniques for Large Language Models (LLMs), focusing on the use of a unique symbolic language combined with social engineering to identify…

    5 2

  3. LLMReadTeamLinguisticDoS LLMReadTeamLinguisticDoS Public

    Exploring "Semantic Re-signification": A novel red teaming technique that induces linguistic denial of service (DoS) and ethical misalignment in Large Language Models (LLMs) by manipulating their c…

    1

  4. RedTeamLowEnthropy RedTeamLowEnthropy Public

    This repository documents ongoing research into Low-Entropy Languages (LEL), an unconventional vector for red teaming large language models (LLMs). An LEL is defined as a non-traditional input syst…