Alternatives and similar repositories for CLIP-MIA

Users that are interested in CLIP-MIA are comparing it to the libraries listed below

• jinhaoduan / SecMI
  [ICML 2023] Are Diffusion Models Vulnerable to Membership Inference Attacks?
  ☆41Updated last year
• bboylyg / RNP
  Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)
  ☆39Updated last year
• umd-huang-lab / VLM-Poisoning
  Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"
  ☆53Updated 8 months ago
• inspire-group / DP-RandP
  [NeurIPS 2023] Differentially Private Image Classification by Learning Priors from Random Processes
  ☆12Updated 2 years ago
• kong13661 / PIA
  Official repo for An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization
  ☆15Updated last year
• WUSTL-CSPL / RIATIG
  ☆27Updated 2 years ago
• jinghuichen / AWM
  Github repo for One-shot Neural Backdoor Erasing via Adversarial Weight Masking (NeurIPS 2022)
  ☆15Updated 2 years ago
• T0hsakar1n / RAPID
  Source code and scripts for the paper "Is Difficulty Calibration All We Need? Towards More Practical Membership Inference Attacks"
  ☆18Updated 9 months ago
• LiangSiyuan21 / BadCLIP
  ☆23Updated last year
• jiawangbai / BadCLIP
  Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdf
  ☆21Updated last year
• KuofengGao / Verbose_Images
  [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images
  ☆39Updated last year
• zqypku / mm_poison
  ☆20Updated last year
• NY1024 / BAP-Jailbreak-Vision-Language-Models-via-Bi-Modal-Adversarial-Prompt
  ☆50Updated last year
• yxoh / prompt_leak_usenix2024
  ☆13Updated last year
• RU-System-Software-and-Security / NONE
  ☆11Updated 2 years ago
• CGCL-codes / TeCo
  [CVPR 2023] The official implementation of our CVPR 2023 paper "Detecting Backdoors During the Inference Stage Based on Corruption Robust…
  ☆23Updated 2 years ago
• csdongxian / ANP_backdoor
  Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"
  ☆58Updated 2 years ago
• GuanlinLee / ART
  Official Code for ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users (NeurIPS 2024)
  ☆16Updated 10 months ago
• AISafety-HKUST / Backdoor_Safety_Tuning
  Backdoor Safety Tuning (NeurIPS 2023 & 2024 Spotlight)
  ☆26Updated 9 months ago
• RU-System-Software-and-Security / BppAttack
  ☆21Updated 3 years ago
• yfchen1994 / poisoning_membership
  ☆20Updated last year
• abc03570128 / Jailbreaking-Attack-against-Multimodal-Large-Language-Model
  ☆48Updated last year
• JunfengGo / SCALE-UP
  ☆24Updated last year
• HanxunH / CognitiveDistillation
  [ICLR2023] Distilling Cognitive Backdoor Patterns within an Image
  ☆36Updated last week
• Jimmy-di / camouflage-poisoning
  Camouflage poisoning via machine unlearning
  ☆17Updated 2 months ago
• SCLBD / DBD
  ☆31Updated 3 years ago
• reds-lab / Meta-Sift
  The official implementation of USENIX Security'23 paper "Meta-Sift" -- Ten minutes or less to find a 1000-size or larger clean subset on …
  ☆19Updated 2 years ago
• grasses / PoisonPrompt
  Code for paper: PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models, IEEE ICASSP 2024. Demo//124.220.228.133:11107
  ☆17Updated last year
• zhaisf / BadT2I
  [MM'23 Oral] "Text-to-image diffusion models can be easily backdoored through multimodal data poisoning"
  ☆31Updated last month
• SCccc21 / Knowledge-Enriched-DMI
  ☆46Updated last year