liudaizong / Awesome-LVLM-Attack
π up-to-date & curated list of awesome Attacks on Large-Vision-Language-Models papers, methods & resources.
β249Updated 2 weeks ago
Alternatives and similar repositories for Awesome-LVLM-Attack:
Users that are interested in Awesome-LVLM-Attack are comparing it to the libraries listed below
- Accepted by IJCAI-24 Survey Trackβ198Updated 7 months ago
- Accepted by ECCV 2024β115Updated 5 months ago
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Promptsβ127Updated last month
- A Survey on Jailbreak Attacks and Defenses against Multimodal Generative Modelsβ144Updated last week
- Safety at Scale: A Comprehensive Survey of Large Model Safetyβ129Updated last month
- A survey on harmful fine-tuning attack for large language modelβ154Updated this week
- Repository for the Paper (AAAI 2024, Oral) --- Visual Adversarial Examples Jailbreak Large Language Modelsβ210Updated 10 months ago
- A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)β140Updated this week
- [NeurIPS-2023] Annual Conference on Neural Information Processing Systemsβ186Updated 3 months ago
- [ICLR 2024 Spotlight π₯ ] - [ Best Paper Award SoCal NLP 2023 π] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modalβ¦β45Updated 9 months ago
- β45Updated 3 months ago
- β43Updated 7 months ago
- β94Updated last year
- Awesome Large Reasoning Model(LRM) Safety.This repository is used to collect security-related research on large reasoning models such as β¦β53Updated this week
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and furβ¦β52Updated 8 months ago
- β123Updated 6 months ago
- β32Updated 3 months ago
- This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2β¦β50Updated last week
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.β61Updated 2 months ago
- β80Updated last month
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Imagesβ32Updated last year
- γACL 2024γ SALAD benchmark & MD-Judgeβ136Updated 3 weeks ago
- Code for ACM MM2024 paper: White-box Multimodal Jailbreaks Against Large Vision-Language Modelsβ23Updated 3 months ago
- β19Updated last month
- BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks on Large Language Modelsβ124Updated last month
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shiβ¦β54Updated 8 months ago
- [ECCV2024] Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectorβ¦β24Updated 4 months ago
- [arXiv:2311.03191] "DeepInception: Hypnotize Large Language Model to Be Jailbreaker"β136Updated last year
- Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)β132Updated 4 months ago
- The reinforcement learning codes for dataset SPA-VLβ31Updated 9 months ago