xiaogang00 / white-paper-for-large-model-security-and-privacy

Related projects ⓘ

Alternatives and complementary repositories for white-paper-for-large-model-security-and-privacy

• hammlab / PoisoningCertifiedDefenses
  How Robust are Randomized Smoothing based Defenses to Data Poisoning? (CVPR 2021)
  ☆12Updated 3 years ago
• Hazelsuko07 / TextHide
  TextHide: Tackling Data Privacy in Language Understanding Tasks
  ☆30Updated 3 years ago
• antsecurity / advml
  AI安全
  ☆34Updated 3 years ago
• papersPapers / BadPrompt
  Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"
  ☆36Updated 4 months ago
• alvinchangw / CARA_EMNLP2020
  Implementation for Poison Attacks against Text Datasets with Conditional Adversarially Regularized Autoencoder (EMNLP-Findings 2020)
  ☆15Updated 4 years ago
• VITA-Group / DP-OPT
  [ICLR'24 Spotlight] DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer
  ☆32Updated 5 months ago
• xinleihe / toxic-prompt
  ☆19Updated last year
• DennisLiu2022 / Membership-Inference-Attacks-by-Exploiting-Loss-Trajectory
  ☆23Updated 2 years ago
• AI-secure / Robustness-Against-Backdoor-Attacks
  RAB: Provable Robustness Against Backdoor Attacks
  ☆39Updated last year
• yfchen1994 / poisoning_membership
  ☆18Updated 6 months ago
• ShawnXYang / AccumulativeAttack
  ☆19Updated 3 years ago
• leix28 / prompt-universal-vulnerability
  Implementation of the paper "Exploring the Universal Vulnerability of Prompt-based Learning Paradigm" on Findings of NAACL 2022
  ☆27Updated 2 years ago
• xlhex / cater_neurips
  ☆6Updated 2 years ago
• IBM / model-sanitization
  Codes for reproducing the results of the paper "Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness" published at IC…
  ☆26Updated 4 years ago
• microsoft / dp-few-shot-generation
  ☆22Updated 11 months ago
• Chriskuei / FedMatch
  CIKM 2021 Full Paper: FedMatch: Federated Learning Over Heterogeneous Question Answering Data
  ☆12Updated 2 years ago
• Sanghyun-Hong / Gradient-Shaping
  [Preprint] On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping
  ☆10Updated 4 years ago
• yjw1029 / EmbMarker
  Code and data for our paper "Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark"…
  ☆47Updated last year
• xlhex / dpnlp
  ☆10Updated 4 years ago
• weichen-yu / LM-Extraction
  ☆40Updated last year
• luxuantao / distill_BERT_into_RNN-CNN
  复现论文《Distilling Task-Specific Knowledge from BERT into Simple Neural Networks》
  ☆14Updated 3 years ago
• liaopeiyuan / GAL
  [ICML 2021] Information Obfuscation of Graph Neural Networks
  ☆36Updated 3 years ago
• Princeton-SysML / FILM
  Official repo for the paper: Recovering Private Text in Federated Learning of Language Models (in NeurIPS 2022)
  ☆57Updated last year
• houcharlie / PrE-Text
  Implementation for PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs
  ☆17Updated 5 months ago
• TrustAIRLab / VoiceJailbreakAttack
  Code for Voice Jailbreak Attacks Against GPT-4o.
  ☆26Updated 5 months ago
• PaddlePaddle / PaddleSleeve
  PaddleSleeve
  ☆77Updated 5 months ago
• PurduePAML / PICCOLO
  ☆23Updated last year
• wyshi / lm_privacy
  ☆18Updated 3 years ago
• SecurityNet-Research / SecurityNet
  ☆12Updated 7 months ago
• wanlunsec / Beatrix
  ☆23Updated last year