Alternatives and similar repositories for SOS

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

• lancopku / RAP
  Code for the paper "RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models" (EMNLP 2021)
  ☆24Updated 3 years ago
• thunlp / HiddenKiller
  Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"
  ☆42Updated 2 years ago
• papersPapers / BadPrompt
  Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"
  ☆39Updated last year
• thunlp / BkdAtk-LWS
  Code and data of the ACL 2021 paper "Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution"
  ☆16Updated 4 years ago
• ShannonAI / backdoor_nlg
  ☆18Updated 4 years ago
• cnut1648 / Model-Fingerprint
  Fingerprint large language models
  ☆41Updated last year
• lishaofeng / NLP_Backdoor
  Hidden backdoor attack on NLP systems
  ☆47Updated 3 years ago
• lancopku / Embedding-Poisoning
  Code for the paper "Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models" (NAACL-…
  ☆41Updated 4 years ago
• alps-lab / trojan-lm
  TrojanLM: Trojaning Language Models for Fun and Profit
  ☆16Updated 4 years ago
• thunlp / NeuBA
  ☆25Updated 4 years ago
• thunlp / StyleAttack
  Code and data of the EMNLP 2021 paper "Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer"
  ☆43Updated 2 years ago
• THU-BPM / unforgeable_watermark
  Source code of paper "An Unforgeable Publicly Verifiable Watermark for Large Language Models" accepted by ICLR 2024
  ☆35Updated last year
• leix28 / prompt-universal-vulnerability
  Implementation of the paper "Exploring the Universal Vulnerability of Prompt-based Learning Paradigm" on Findings of NAACL 2022
  ☆30Updated 3 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
• THU-BPM / Robust_Watermark
  Code and data for paper "A Semantic Invariant Robust Watermark for Large Language Models" accepted by ICLR 2024.
  ☆34Updated 9 months ago
• bangawayoo / nlp-watermarking
  Robust natural language watermarking using invariant features
  ☆26Updated last year
• PurduePAML / PICCOLO
  ☆25Updated 2 years ago
• HKUST-KnowComp / LLM-Multistep-Jailbreak
  Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT
  ☆34Updated last year
• PurduePAML / DBS
  ☆18Updated 3 years ago
• byerose / Awesome-Foundation-Model-Security
  A curated list of trustworthy Generative AI papers. Daily updating...
  ☆73Updated 11 months ago
• thunlp / OpenBackdoor
  An open-source toolkit for textual backdoor attack and defense (NeurIPS 2022 D&B, Spotlight)
  ☆189Updated 2 years ago
• facebookresearch / text-adversarial-attack
  Repo for arXiv preprint "Gradient-based Adversarial Attacks against Text Transformers"
  ☆108Updated 2 years ago
• yfchen1994 / poisoning_membership
  ☆20Updated last year
• Kiode / Text_Watermark
  Watermarking Text Generated by Black-Box Language Models
  ☆39Updated last year
• leileigan / clean_label_textual_backdoor_attack
  ☆18Updated 3 years ago
• SCLBD / DBD
  ☆31Updated 3 years ago
• qingjiesjtu / USC
  This is the code repository of our submission: Understanding the Dark Side of LLMs’ Intrinsic Self-Correction.
  ☆61Updated 8 months ago
• ethz-spylab / rlhf-poisoning
  Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"
  ☆57Updated last year
• YancyKahn / CoA
  Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM
  ☆34Updated 7 months ago
• ThuCCSLab / MergeGuard
  [CCS-LAMPS'24] LLM IP Protection Against Model Merging
  ☆15Updated 10 months ago