Alternatives and similar repositories for Visual-Adversarial-Examples-Jailbreak-Large-Language-Models:

Users that are interested in Visual-Adversarial-Examples-Jailbreak-Large-Language-Models are comparing it to the libraries listed below

• ThuCCSLab / FigStep
  [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts
  ☆108Updated 2 months ago
• isXinLiu / MM-SafetyBench
  Accepted by ECCV 2024
  ☆94Updated 4 months ago
• liudaizong / Awesome-LVLM-Attack
  😎 up-to-date & curated list of awesome Attacks on Large-Vision-Language-Models papers, methods & resources.
  ☆206Updated this week
• thu-ml / Attack-Bard
  ☆92Updated last year
• isXinLiu / Awesome-MLLM-Safety
  Accepted by IJCAI-24 Survey Track
  ☆190Updated 5 months ago
• euanong / image-hijacks
  Official codebase for Image Hijacks: Adversarial Images can Control Generative Models at Runtime
  ☆42Updated last year
• erfanshayegani / Jailbreak-In-Pieces
  [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…
  ☆38Updated 8 months ago
• yunqing-me / AttackVLM
  [NeurIPS-2023] Annual Conference on Neural Information Processing Systems
  ☆178Updated last month
• AI45Lab / ActorAttack
  ☆72Updated last week
• git-disl / awesome_LLM-harmful-fine-tuning-papers
  A survey on harmful fine-tuning attack for large language model
  ☆135Updated last week
• thunxxx / MLLM-Jailbreak-evaluation-MMJ-Bench
  ☆27Updated 2 months ago
• thu-ml / MMTrustEval
  A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)
  ☆126Updated this week
• RUCAIBox / HADES
  [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …
  ☆16Updated 3 months ago
• EddyLuo1232 / JailBreakV_28K
  [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…
  ☆46Updated 7 months ago
• rotaryhammer / code-autodan
  An unofficial implementation of AutoDAN attack on LLMs (arXiv:2310.15140)
  ☆35Updated last year
• abc03570128 / Jailbreaking-Attack-against-Multimodal-Large-Language-Model
  ☆40Updated 6 months ago
• facebookresearch / advprompter
  Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873
  ☆139Updated 9 months ago
• tmlr-group / DeepInception
  [arXiv:2311.03191] "DeepInception: Hypnotize Large Language Model to Be Jailbreaker"
  ☆133Updated 11 months ago
• UCSC-VLAA / vllm-safety-benchmark
  [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"
  ☆76Updated last year
• GodXuxilie / PromptAttack
  An LLM can Fool Itself: A Prompt-Based Adversarial Attack (ICLR 2024)
  ☆75Updated 3 weeks ago
• ys-zong / VLGuard
  [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.
  ☆52Updated 3 weeks ago
• NY1024 / Foundation-Model-Paper-Notes
  ☆37Updated last month
• sail-sg / AnyDoor
  AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Models
  ☆48Updated 10 months ago
• Haochen-Luo / CroPA
  ☆34Updated 2 months ago
• byerose / Awesome-Foundation-Model-Security
  A curated list of trustworthy Generative AI papers. Daily updating...
  ☆68Updated 5 months ago
• xyq7 / GradSafe
  Official Code for ACL 2024 paper "GradSafe: Detecting Unsafe Prompts for LLMs via Safety-Critical Gradient Analysis"
  ☆49Updated 3 months ago
• liuxuannan / Awesome-Multimodal-Jailbreak
  A Survey on Jailbreak Attacks and Defenses against Multimodal Generative Models
  ☆121Updated last week
• Princeton-SysML / Jailbreak_LLM
  ☆162Updated last year
• ThuCCSLab / JailbreakEval
  [NDSS'25 Poster] A collection of automated evaluators for assessing jailbreak attempts.
  ☆108Updated 3 weeks ago
• eurekayuan / RigorLLM
  Implementation for "RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content"
  ☆20Updated 6 months ago