hcliucs/APSD

[NeurIPS, 500+ Citations!] Alignment & Safety for multimodal foundation models

Official repository for "On Generating Transferable Targeted Perturbations" (ICCV 2021)

Open-source cross-modal and multimodal prompt injection test suite. 250,000+ attack payloads across text, image, document, and audio modalities. Research-backed by OWASP LLM Top 10, CrossInject (ACM MM 2025), FigStep (AAAI 2025), DolphinAttack, and CSA 2026.

😎 up-to-date & curated list of awesome Attacks on Large-Vision-Language-Models papers, methods & resources.

[ICML'26] SICA & OpenMMSec

[ACM MM 2026] Code for paper "Omni-SafetyBench: A Benchmark for Safety Evaluation of Audio-Visual Large Language Models".

A collection of resources on attacks and defenses targeting text-to-image diffusion models

TransferAttack is a pytorch framework to boost the adversarial transferability for image classification.