Alternatives and similar repositories for llm_defends

Users that are interested in llm_defends are comparing it to the libraries listed below

• David-Li0406 / AI-Supervision-Risk
  ☆20Updated 2 months ago
• princeton-nlp / benign-data-breaks-safety
  ☆41Updated 8 months ago
• YancyKahn / CoA
  Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM
  ☆31Updated 4 months ago
• shuaizhao95 / ICLAttack
  ICL backdoor attack
  ☆12Updated 7 months ago
• llm-editing / editing-attack
  Code and dataset for the paper: "Can Editing LLMs Inject Harm?"
  ☆19Updated 6 months ago
• swj0419 / muse_bench
  ☆21Updated 2 months ago
• thu-coai / JailbreakDefense_GoalPriority
  [ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization
  ☆24Updated 10 months ago
• papersPapers / BadPrompt
  Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"
  ☆36Updated 10 months ago
• YihanWang617 / llm-jailbreaking-defense
  A lightweight library for large laguage model (LLM) jailbreaking defense.
  ☆51Updated 7 months ago
• inspire-group / RobustRAG
  ☆18Updated 8 months ago
• AISG-Technology-Team / GCSS-Track-1A-Submission-Guide
  Submission Guide + Discussion Board for AI Singapore Global Challenge for Safe and Secure LLMs (Track 1A).
  ☆16Updated 11 months ago
• yjw1029 / Self-Reminder-Data
  Data for our paper "Defending ChatGPT against Jailbreak Attack via Self-Reminder"
  ☆18Updated last year
• leix28 / prompt-universal-vulnerability
  Implementation of the paper "Exploring the Universal Vulnerability of Prompt-based Learning Paradigm" on Findings of NAACL 2022
  ☆29Updated 2 years ago
• git-disl / Vaccine
  This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)
  ☆43Updated 6 months ago
• lapisrocks / rpo
  Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"
  ☆53Updated 9 months ago
• jinzhuoran / RWKU
  RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024
  ☆75Updated 8 months ago
• HKUST-KnowComp / LLM-Multistep-Jailbreak
  Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT
  ☆33Updated last year
• sail-sg / closer-look-LLM-unlearning
  [ICLR 2025] A Closer Look at Machine Unlearning for Large Language Models
  ☆29Updated 6 months ago
• yjw1029 / Self-Reminder
  Code for our paper "Defending ChatGPT against Jailbreak Attack via Self-Reminder" in NMI.
  ☆49Updated last year
• wegodev2 / virtual-prompt-injection
  Unofficial implementation of "Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection"
  ☆18Updated 11 months ago
• SORRY-Bench / sorry-bench
  Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)
  ☆54Updated 3 months ago
• SALT-NLP / Efficient_Unlearning
  ☆38Updated last year
• BeyonderXX / ShadowAlignment
  Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models
  ☆29Updated last year
• RockyLzy / TextDefender
  codes for "Searching for an Effective Defender:Benchmarking Defense against Adversarial Word Substitution"
  ☆31Updated last year
• thunlp / HiddenKiller
  Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"
  ☆43Updated 2 years ago
• sophie-xhonneux / Continuous-AdvTrain
  ☆22Updated 9 months ago
• princeton-nlp / corpus-poisoning
  [EMNLP 2023] Poisoning Retrieval Corpora by Injecting Adversarial Passages https://arxiv.org/abs/2310.19156
  ☆33Updated last year
• BruthYU / MELO
  [AAAI 2024] MELO: Enhancing Model Editing with Neuron-indexed Dynamic LoRA
  ☆9Updated last year
• deeplearning-wisc / picle
  Official code for ICML 2024 paper on Persona In-Context Learning (PICLe)
  ☆24Updated 11 months ago
• wang2226 / Trojan-Activation-Attack
  [CIKM 2024] Trojan Activation Attack: Attack Large Language Models using Activation Steering for Safety-Alignment.
  ☆23Updated 10 months ago