Alternatives and similar repositories for prompt-universal-vulnerability

Users that are interested in prompt-universal-vulnerability are comparing it to the libraries listed below

• lancopku / Embedding-Poisoning
  Code for the paper "Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models" (NAACL-…
  ☆42Updated 4 years ago
• AlexWan0 / Poisoning-Instruction-Tuned-Models
  ☆56Updated last year
• thunlp / NeuBA
  ☆25Updated 4 years ago
• Yangyi-Chen / PaperList-Trustworthy-Applications
  Mostly recording papers about models' trustworthy applications. Intending to include topics like model evaluation & analysis, security, c…
  ☆21Updated 2 years ago
• thunlp / ONION
  Official implementation of the EMNLP 2021 paper "ONION: A Simple and Effective Defense Against Textual Backdoor Attacks"
  ☆34Updated 3 years ago
• lancopku / RAP
  Code for the paper "RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models" (EMNLP 2021)
  ☆25Updated 3 years ago
• Vaidehi99 / InfoDeletionAttacks
  ☆46Updated 7 months ago
• lancopku / SOS
  Code for the paper "Rethinking Stealthiness of Backdoor Attack against NLP Models" (ACL-IJCNLP 2021)
  ☆24Updated 3 years ago
• papersPapers / BadPrompt
  Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"
  ☆39Updated last year
• thunlp / HiddenKiller
  Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"
  ☆43Updated 3 years ago
• yjw1029 / Self-Reminder-Data
  Data for our paper "Defending ChatGPT against Jailbreak Attack via Self-Reminder"
  ☆20Updated last year
• YihanWang617 / llm-jailbreaking-defense
  A lightweight library for large laguage model (LLM) jailbreaking defense.
  ☆57Updated 3 weeks ago
• THU-BPM / Robust_Watermark
  Code and data for paper "A Semantic Invariant Robust Watermark for Large Language Models" accepted by ICLR 2024.
  ☆34Updated 10 months ago
• RockyLzy / TextDefender
  codes for "Searching for an Effective Defender:Benchmarking Defense against Adversarial Word Substitution"
  ☆31Updated last year
• QData / TextAttack-A2T
  A2T: Towards Improving Adversarial Training of NLP Models (EMNLP 2021 Findings)
  ☆26Updated 4 years ago
• thu-coai / Targeted-Data-Extraction
  Official Code for ACL 2023 paper: "Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confid…
  ☆23Updated 2 years ago
• SafeAILab / RAIN
  [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning
  ☆98Updated last year
• facebookresearch / text-adversarial-attack
  Repo for arXiv preprint "Gradient-based Adversarial Attacks against Text Transformers"
  ☆109Updated 2 years ago
• Hsuan-Tung / universal_attack_natural_trigger
  Natural Universal Trigger Search (NUTS)
  ☆21Updated 4 years ago
• dugu9sword / dne
  ACL 2021 - Defense against Adversarial Attacks in NLP via Dirichlet Neighborhood Ensemble
  ☆18Updated 2 years ago
• weichen-yu / LM-Extraction
  ☆43Updated 2 years ago
• Princeton-SysML / kNNLM_privacy
  Official implementation of Privacy Implications of Retrieval-Based Language Models (EMNLP 2023). https://arxiv.org/abs/2305.14888
  ☆36Updated last year
• VITA-Group / DP-OPT
  [ICLR'24 Spotlight] DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer
  ☆46Updated last year
• cookielee77 / CLARE
  Contextualized Perturbation for Textual Adversarial Attack, NAACL 2021
  ☆43Updated 4 years ago
• xinleihe / toxic-prompt
  ☆26Updated last year
• joeljang / knowledge-unlearning
  [ACL 2023] Knowledge Unlearning for Mitigating Privacy Risks in Language Models
  ☆82Updated last year
• SALT-NLP / Efficient_Unlearning
  ☆38Updated last year
• vinid / safety-tuned-llamas
  ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.
  ☆87Updated last year
• David-Li0406 / AI-Supervision-Risk
  ☆21Updated 6 months ago
• YihanWang617 / LLM-Jailbreaking-Defense-Backtranslation
  Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"
  ☆30Updated last year