Stars
Official DeepSound repository migrated from jpinsoft.net. DeepSound is a freeware steganography tool and audio converter that hides secret data into audio files. The application also enables you to…
A multi-threaded PDF password cracking utility equipped with commonly encountered password format builders and dictionary attacks.
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
⚡ Worlds fastest steghide cracker, chewing through millions of passwords per second ⚡
The Official Bash Bunny Payload Repository
Trustworthy AI: From Theory to Practice book. Explore the intersection of ethics and technology with 'Trustworthy AI: From Theory to Practice.' This comprehensive guide delves into creating AI mode…
A beginner friendly repository for getting started with adversarial machine learning in PyTorch
As seen at DEF CON and O'Reilly Live Trainings
Reading list of more resources to learn about Adversarial Attacks on AI Systems
Adversarial machine learning for a DNN for malware classification
A System-Oriented Wargame Framework for Adversarial ML
An awesome & curated list of best LLMOps tools for developers
[ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"
AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Models
Repository for the Paper: Refusing Safe Prompts for Multi-modal Large Language Models
[Arxiv 2024] Adversarial attacks on multimodal agents
[ICML2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast
Repository for the Paper (AAAI 2024, Oral) --- Visual Adversarial Examples Jailbreak Large Language Models
This repository includes samples of audio provided to different chatbots. Some of these samples have been modified to contain concealed messages. When these altered audios are converted by an audio…
A side channel attack on the acoustic signal of the typing sounds in order to get the typed data and produce smart dictionary attacks on passwords
[ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models''
PhD/MSc course on Machine Learning Security (Univ. Cagliari)
AIBOM Workshop at SBOM-a-Rama (Fall 2024)
USB mouse traffic packet forensic tool, mainly used to draw mouse movements and dragging trajectories
An unrestricted attack based on diffusion models that can achieve both good transferability and imperceptibility.
This is a collection of awesome papers I have read (carefully or roughly) in the fields of security in diffusion models. Any suggestions and comments are welcome ([email protected]).
[CVPR23W] "A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion" by Haomin Zhuang, Yihua Zhang and Sijia Liu