Repositories list

• X-Boundary

  Public
  The code repo of paper "X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Multi-Turn Jailbreaks without Compromising Usability"

  Python

  •0•2•0•0•Updated Feb 17, 2025Feb 17, 2025

• CELLO

  Public
  Python

  •

  Apache License 2.0

  •0•0•0•0•Updated Feb 13, 2025Feb 13, 2025

• MORE

  Public
  JavaScript

  •

  Apache License 2.0

  •0•0•0•0•Updated Feb 13, 2025Feb 13, 2025

• SelfConsciousness

  Public
  Python

  •

  Apache License 2.0

  •0•0•0•0•Updated Feb 13, 2025Feb 13, 2025

• CaLM

  Public
  Python

  •

  Apache License 2.0

  •0•0•0•0•Updated Feb 13, 2025Feb 13, 2025

• ADCE

  Public
  The official code for paper: Beyond Surface Structure: A Causal Assessment of LLMs' Comprehension ability.

  Python

  •1•0•0•0•Updated Feb 13, 2025Feb 13, 2025

• SEER

  Public
  Self-Explainability Enhancement of LLMs’ Representations

  Python

  •0•5•0•0•Updated Feb 11, 2025Feb 11, 2025

• ActorAttack

  Public
  Python

  •3•74•0•0•Updated Feb 3, 2025Feb 3, 2025

• ReflectionBench

  Public
  ReflectionBench

  Python

  •2•8•1•0•Updated Jan 20, 2025Jan 20, 2025

• VLSBench

  Public
  Data and Code for Paper VLSBench: Unveiling Visual Leakage in Multimodal Safety

  Python

  •1•30•1•0•Updated Jan 17, 2025Jan 17, 2025

• MM-SafetyBench

  Public
  Python

  •0•0•0•0•Updated Jan 17, 2025Jan 17, 2025

• ESC-Eval

  Public
  Python

  •0•1•0•0•Updated Jan 17, 2025Jan 17, 2025

• emulated-disalignment

  Public
  Python

  •0•0•0•0•Updated Jan 17, 2025Jan 17, 2025

• weak-to-strong-search

  Public
  Python

  •0•2•0•0•Updated Jan 17, 2025Jan 17, 2025

• modpo

  Public
  Python

  •0•0•0•0•Updated Jan 17, 2025Jan 17, 2025

• .github

  Public
  0•0•0•0•Updated Jan 16, 2025Jan 16, 2025

• SALAD-BENCH

  Public
  【ACL 2024】 SALAD benchmark & MD-Judge

  Python

  •

  Apache License 2.0

  •0•1•0•0•Updated Jan 16, 2025Jan 16, 2025

• REEF

  Public
  The repository of the paper "REEF: Representation Encoding Fingerprints for Large Language Models," aims to protect the IP of open-source LLMs.

  Python

  •3•40•0•0•Updated Jan 16, 2025Jan 16, 2025

• CredID

  Public
  Python

  •1•0•0•0•Updated Dec 26, 2024Dec 26, 2024

• AIGC_detection

  Public
  Makefile

  •

  The Unlicense

  •0•0•0•5•Updated Dec 23, 2024Dec 23, 2024

• T2ISafety

  Public
  0•1•0•0•Updated Nov 25, 2024Nov 25, 2024

• DEAN

  Public
  Python

  •

  Apache License 2.0

  •1•10•0•0•Updated Oct 25, 2024Oct 25, 2024

• CodeAttack

  Public
  [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion

  Python

  •

  MIT License

  •3•36•1•1•Updated Oct 25, 2024Oct 25, 2024

• MLLMGuard

  Public
  Python

  •2•21•2•0•Updated Oct 22, 2024Oct 22, 2024

• ivg

  Public
  Official repository of the paper "Inference-Time Language Model Alignment via Integrated Value Guidance"

  Python

  •0•0•0•0•Updated Sep 27, 2024Sep 27, 2024

• Persafety

  Public
  The repository of paper "The Better Angels of Machine Personality: How Personality Relates to LLM Safety".

  0•3•0•0•Updated Jul 2, 2024Jul 2, 2024

• TracingLLM

  Public
  Python

  •

  Apache License 2.0

  •4•0•0•0•Updated May 22, 2024May 22, 2024

• Flames

  Public
  Flames is a highly adversarial benchmark in Chinese for LLM's harmlessness evaluation developed by Shanghai AI Lab and Fudan NLP Group.

  Apache License 2.0

  •0•41•1•0•Updated May 21, 2024May 21, 2024

• Fake-Alignment

  Public
  Python

  •

  Apache License 2.0

  •0•5•0•0•Updated Mar 22, 2024Mar 22, 2024