Best AI tools for< protect users from harmful content >

NSFW.js is a client-side indecent content checking tool that uses AI to detect and blur inappropriate images. It is designed to protect users from being exposed to harmful or offensive content online. The tool is easy to use and can be integrated into any website or application. It is also highly accurate and can detect even the most subtle forms of indecent content.

Checkstep is an AI-powered content moderation platform that helps businesses detect and remove harmful content from their platforms. It offers a range of features, including image, text, audio, and video moderation, as well as compliance reporting and moderation tools. Checkstep's platform is designed to be easy to use and integrate, and it can be customized to meet the specific needs of each business.

Link Shield is an AI-powered malicious URL detection API platform that helps protect online security. It utilizes advanced machine learning algorithms to analyze URLs and identify suspicious activity, safeguarding users from phishing scams, malware, and other harmful threats. The API is designed for ease of integration, affordability, and flexibility, making it accessible to developers of all levels. Link Shield empowers businesses to ensure the safety and security of their applications and online communities.

Deepfake Detector is a tool that helps users detect if an audio or video is a deepfake or not using AI. It is designed to protect users from misinformation and deception by filtering out AI-generated videos and audios. The tool is easy to use and provides accurate results. It is a valuable tool for anyone who wants to ensure the authenticity of videos and audios.

LoginLlama is a suspicious login detection tool that helps developers prevent fraudulent logins to their applications. It uses a combination of AI and machine learning to analyze login attempts and identify suspicious activity. LoginLlama is easy to integrate with any application using its REST API or official libraries. It provides a single endpoint and requires only a few lines of code to implement. LoginLlama offers a free trial with 1000 free login checks and has three pricing plans starting at $19/month.

SafeSpeak is an AI-powered mobile security solution that protects users from phone scams, SIM swaps, and other malicious activities. It uses advanced machine learning and large language models to detect and block threats in real-time. SafeSpeak offers a range of features for both personal and business use, including malicious behavior detection, community immunity, SIM swap detection, weekly and monthly reporting, quick and easy setup, admin dashboard, extensible API, custom reporting, and visibility into tactics, techniques, and procedures (TTPs).

AI or Not is an AI-powered tool that helps businesses and individuals detect AI-generated images and audio. It uses advanced machine learning algorithms to analyze content and determine the likelihood of AI manipulation. With AI or Not, users can protect themselves from fraud, misinformation, and other malicious activities involving AI-generated content.

Blackbird.AI is a narrative and risk intelligence platform that helps organizations identify and protect against narrative attacks created by misinformation and disinformation. The platform offers a range of solutions tailored to different industries and roles, enabling users to analyze threats in text, images, and memes across various sources such as social media, news, and the dark web. By providing context and clarity for strategic decision-making, Blackbird.AI empowers organizations to proactively manage and mitigate the impact of narrative attacks on their reputation and financial stability.

Protect AI is a comprehensive platform designed to secure AI systems by providing visibility and manageability to detect and mitigate unique AI security threats. The platform empowers organizations to embrace a security-first approach to AI, offering solutions for AI Security Posture Management, ML model security enforcement, AI/ML supply chain vulnerability database, LLM security monitoring, and observability. Protect AI aims to safeguard AI applications and ML systems from potential vulnerabilities, enabling users to build, adopt, and deploy AI models confidently and at scale.

MacWhisper is a native macOS application that utilizes OpenAI's Whisper technology for transcribing audio files into text. It offers a user-friendly interface for recording, transcribing, and editing audio, making it suitable for various use cases such as transcribing meetings, lectures, interviews, and podcasts. The application is designed to protect user privacy by performing all transcriptions locally on the device, ensuring that no data leaves the user's machine.

Alcion is a backup-as-a-service solution designed specifically for Microsoft 365 users. It offers a secure backup solution driven by AI technology to protect data from ransomware, malware, accidents, and outages. Alcion provides a user-friendly experience with features like intelligent backups, robust data protection, security, and compliance. The platform is built to be easy to use, efficient, and reliable, ensuring that users can quickly set up backups and restore data when needed. Alcion is trusted by Microsoft 365 admins globally for its advanced AI-driven approach to data protection.

ZeroGPT is a free AI content detector that helps users identify AI-generated text. It uses machine learning algorithms and natural language processing techniques to analyze text and determine whether it was written by a human or an AI. ZeroGPT is accurate, fast, and easy to use. It can be used to detect AI-generated text in a variety of languages, including English, Spanish, French, German, and Chinese. ZeroGPT is a valuable tool for anyone who wants to ensure that their content is original and authentic.

GoPDF is a free online PDF editor and AI-powered PDF management tool that allows users to create, manage, convert, eSign, and edit PDF documents from anywhere in the world. It offers a wide range of features including PDF editing, PDF to JPG conversion, PDF to Word conversion, PDF compression, PDF merging, PDF protection, PDF filling and signing, PDF search and replace, PDF cropping, and OCR PDF. GoPDF is designed to simplify PDF management and make it easy for users to work with PDF documents.

hCaptcha Enterprise is a comprehensive security platform that protects businesses from a wide range of online threats, including bots, fraud, and abuse. It uses advanced machine learning and threat intelligence to detect and block malicious activity, while providing a frictionless experience for legitimate users. hCaptcha Enterprise is easy to deploy and manage, and it can be customized to meet the specific needs of each business.

WatermarkRemover is an AI-powered tool that allows users to remove unwanted watermarks from their images. It utilizes advanced image processing algorithms to effectively erase watermarks while preserving the integrity of the original image. The tool is designed to be user-friendly and accessible, enabling anyone to easily remove watermarks from their photos.

BladeRunner is a browser plug-in that highlights AI-generated text directly on the page. It helps users detect AI-generated content in various online platforms, such as social media, news, education, e-commerce, and government communications. In the age of AI, where distinguishing between human and AI-generated content is challenging, BladeRunner serves as a tool to aid users in identifying AI impostors and maintaining accuracy in digital interactions.

Twilight is an AI-driven productivity platform designed to help busy individuals stay ahead of their schedule effortlessly. It offers features such as scheduling and rescheduling meetings, copying OTPs, summarizing content, and more. The platform focuses on simplicity, reliability, and efficiency, aiming to empower users to focus on what truly matters and enhance their workflow.

Atom.com is a website that utilizes Cloudflare's security service to protect itself from online attacks. Users may encounter a block when certain actions trigger the security solution. In such cases, users can contact the site owner to resolve the issue by providing details of the incident. Cloudflare Ray ID is used to identify the specific block trigger. The website focuses on maintaining performance and security for its users.

Wing Security is a SaaS Security Posture Management (SSPM) solution that helps businesses protect their data by providing full visibility and control over applications, users, and data. The platform offers features such as automated remediation, AI discovery, real-time SaaS visibility, vendor risk management, insider risk management, and more. Wing Security enables organizations to eliminate risky applications, manage user behavior, and protect sensitive data from unauthorized access. With a focus on security first, Wing Security helps businesses leverage the benefits of SaaS while staying protected.

Kupid.ai is an AI-powered platform that focuses on enhancing online security and user verification processes. It utilizes advanced algorithms to verify the authenticity of users and ensure secure connections. By leveraging AI technology, Kupid.ai offers a seamless and efficient verification experience, helping businesses protect their online platforms from potential threats and fraudulent activities.

last_layer is a security library designed to protect LLM applications from prompt injection attacks, jailbreaks, and exploits. It acts as a robust filtering layer to scrutinize prompts before they are processed by LLMs, ensuring that only safe and appropriate content is allowed through. The tool offers ultra-fast scanning with low latency, privacy-focused operation without tracking or network calls, compatibility with serverless platforms, advanced threat detection mechanisms, and regular updates to adapt to evolving security challenges. It significantly reduces the risk of prompt-based attacks and exploits but cannot guarantee complete protection against all possible threats.

Talemate is a roleplay tool that allows users to interact with AI agents for dialogue, narration, summarization, direction, editing, world state management, character/scenario creation, text-to-speech, and visual generation. It supports multiple AI clients and APIs, offers long-term memory using ChromaDB, and provides tools for managing NPCs, AI-assisted character creation, and scenario creation. Users can customize prompts using Jinja2 templates and benefit from a modern, responsive UI. The tool also integrates with Runpod for enhanced functionality.

SeaLLMs are a family of language models optimized for Southeast Asian (SEA) languages. They were pre-trained from Llama-2, on a tailored publicly-available dataset, which comprises texts in Vietnamese 🇻🇳, Indonesian 🇮🇩, Thai 🇹🇭, Malay 🇲🇾, Khmer🇰🇭, Lao🇱🇦, Tagalog🇵🇭 and Burmese🇲🇲. The SeaLLM-chat underwent supervised finetuning (SFT) and specialized self-preferencing DPO using a mix of public instruction data and a small number of queries used by SEA language native speakers in natural settings, which **adapt to the local cultural norms, customs, styles and laws in these areas**. SeaLLM-13b models exhibit superior performance across a wide spectrum of linguistic tasks and assistant-style instruction-following capabilities relative to comparable open-source models. Moreover, they outperform **ChatGPT-3.5** in non-Latin languages, such as Thai, Khmer, Lao, and Burmese.

ZenGuard AI enables AI developers to integrate production-level, low-code LLM (Large Language Model) guardrails into their generative AI applications effortlessly. With ZenGuard AI, ensure your application operates within trusted boundaries, is protected from prompt injections, and maintains user privacy without compromising on performance.

InternLM is a powerful language model series with features such as 200K context window for long-context tasks, outstanding comprehensive performance in reasoning, math, code, chat experience, instruction following, and creative writing, code interpreter & data analysis capabilities, and stronger tool utilization capabilities. It offers models in sizes of 7B and 20B, suitable for research and complex scenarios. The models are recommended for various applications and exhibit better performance than previous generations. InternLM models may match or surpass other open-source models like ChatGPT. The tool has been evaluated on various datasets and has shown superior performance in multiple tasks. It requires Python >= 3.8, PyTorch >= 1.12.0, and Transformers >= 4.34 for usage. InternLM can be used for tasks like chat, agent applications, fine-tuning, deployment, and long-context inference.

h2oGPT is an Apache V2 open-source project that allows users to query and summarize documents or chat with local private GPT LLMs. It features a private offline database of any documents (PDFs, Excel, Word, Images, Video Frames, Youtube, Audio, Code, Text, MarkDown, etc.), a persistent database (Chroma, Weaviate, or in-memory FAISS) using accurate embeddings (instructor-large, all-MiniLM-L6-v2, etc.), and efficient use of context using instruct-tuned LLMs (no need for LangChain's few-shot approach). h2oGPT also offers parallel summarization and extraction, reaching an output of 80 tokens per second with the 13B LLaMa2 model, HYDE (Hypothetical Document Embeddings) for enhanced retrieval based upon LLM responses, a variety of models supported (LLaMa2, Mistral, Falcon, Vicuna, WizardLM. With AutoGPTQ, 4-bit/8-bit, LORA, etc.), GPU support from HF and LLaMa.cpp GGML models, and CPU support using HF, LLaMa.cpp, and GPT4ALL models. Additionally, h2oGPT provides Attention Sinks for arbitrarily long generation (LLaMa-2, Mistral, MPT, Pythia, Falcon, etc.), a UI or CLI with streaming of all models, the ability to upload and view documents through the UI (control multiple collaborative or personal collections), Vision Models LLaVa, Claude-3, Gemini-Pro-Vision, GPT-4-Vision, Image Generation Stable Diffusion (sdxl-turbo, sdxl) and PlaygroundAI (playv2), Voice STT using Whisper with streaming audio conversion, Voice TTS using MIT-Licensed Microsoft Speech T5 with multiple voices and Streaming audio conversion, Voice TTS using MPL2-Licensed TTS including Voice Cloning and Streaming audio conversion, AI Assistant Voice Control Mode for hands-free control of h2oGPT chat, Bake-off UI mode against many models at the same time, Easy Download of model artifacts and control over models like LLaMa.cpp through the UI, Authentication in the UI by user/password via Native or Google OAuth, State Preservation in the UI by user/password, Linux, Docker, macOS, and Windows support, Easy Windows Installer for Windows 10 64-bit (CPU/CUDA), Easy macOS Installer for macOS (CPU/M1/M2), Inference Servers support (oLLaMa, HF TGI server, vLLM, Gradio, ExLLaMa, Replicate, OpenAI, Azure OpenAI, Anthropic), OpenAI-compliant, Server Proxy API (h2oGPT acts as drop-in-replacement to OpenAI server), Python client API (to talk to Gradio server), JSON Mode with any model via code block extraction. Also supports MistralAI JSON mode, Claude-3 via function calling with strict Schema, OpenAI via JSON mode, and vLLM via guided_json with strict Schema, Web-Search integration with Chat and Document Q/A, Agents for Search, Document Q/A, Python Code, CSV frames (Experimental, best with OpenAI currently), Evaluate performance using reward models, and Quality maintained with over 1000 unit and integration tests taking over 4 GPU-hours.

Awesome-Segment-Anything is a powerful tool for segmenting and extracting information from various types of data. It provides a user-friendly interface to easily define segmentation rules and apply them to text, images, and other data formats. The tool supports both supervised and unsupervised segmentation methods, allowing users to customize the segmentation process based on their specific needs. With its versatile functionality and intuitive design, Awesome-Segment-Anything is ideal for data analysts, researchers, content creators, and anyone looking to efficiently extract valuable insights from complex datasets.

This competition is organized by Javier Rando and Florian Tramèr from the ETH AI Center and SPY Lab at ETH Zurich. The goal of the competition is to create a method that can detect universal backdoors in aligned language models. A universal backdoor is a secret suffix that, when appended to any prompt, enables the model to answer harmful instructions. The competition provides a set of poisoned generation models, a reward model that measures how safe a completion is, and a dataset with prompts to run experiments. Participants are encouraged to use novel methods for red-teaming, automated approaches with low human oversight, and interpretability tools to find the trojans. The best submissions will be offered the chance to present their work at an event during the SaTML 2024 conference and may be invited to co-author a publication summarizing the competition results.

KULLM (구름) is a Korean Large Language Model developed by Korea University NLP & AI Lab and HIAI Research Institute. It is based on the upstage/SOLAR-10.7B-v1.0 model and has been fine-tuned for instruction. The model has been trained on 8×A100 GPUs and is capable of generating responses in Korean language. KULLM exhibits hallucination and repetition phenomena due to its decoding strategy. Users should be cautious as the model may produce inaccurate or harmful results. Performance may vary in benchmarks without a fixed system prompt.

Simple-OpenAI is a Java library that provides a simple way to interact with the OpenAI API. It offers consistent interfaces for various OpenAI services like Audio, Chat Completion, Image Generation, and more. The library uses CleverClient for HTTP communication, Jackson for JSON parsing, and Lombok to reduce boilerplate code. It supports asynchronous requests and provides methods for synchronous calls as well. Users can easily create objects to communicate with the OpenAI API and perform tasks like text-to-speech, transcription, image generation, and chat completions.

EasyEdit is a Python package for edit Large Language Models (LLM) like `GPT-J`, `Llama`, `GPT-NEO`, `GPT2`, `T5`(support models from **1B** to **65B**), the objective of which is to alter the behavior of LLMs efficiently within a specific domain without negatively impacting performance across other inputs. It is designed to be easy to use and easy to extend.

TrustLLM is a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions. Specifically, we first propose a set of principles for trustworthy LLMs that span eight different dimensions. Based on these principles, we further establish a benchmark across six dimensions including truthfulness, safety, fairness, robustness, privacy, and machine ethics. We then present a study evaluating 16 mainstream LLMs in TrustLLM, consisting of over 30 datasets. The document explains how to use the trustllm python package to help you assess the performance of your LLM in trustworthiness more quickly. For more details about TrustLLM, please refer to project website.

TTS Generation WebUI is a comprehensive tool that provides a user-friendly interface for text-to-speech and voice cloning tasks. It integrates various AI models such as Bark, MusicGen, AudioGen, Tortoise, RVC, Vocos, Demucs, SeamlessM4T, and MAGNeT. The tool offers one-click installers, Google Colab demo, videos for guidance, and extra voices for Bark. Users can generate audio outputs, manage models, caches, and system space for AI projects. The project is open-source and emphasizes ethical and responsible use of AI technology.

Giskard is an open-source Python library that automatically detects performance, bias & security issues in AI applications. The library covers LLM-based applications such as RAG agents, all the way to traditional ML models for tabular data.

The Prompt Fuzzer is an open-source tool that helps you assess the security of your GenAI application's system prompt against various dynamic LLM-based attacks. It provides a security evaluation based on the outcome of these attack simulations, enabling you to strengthen your system prompt as needed. The Prompt Fuzzer dynamically tailors its tests to your application's unique configuration and domain. The Fuzzer also includes a Playground chat interface, giving you the chance to iteratively improve your system prompt, hardening it against a wide spectrum of generative AI attacks.

This is the official repository for the ACM CCS 2024 paper 'Do Anything Now': Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models. The project employs a new framework called JailbreakHub to conduct the first measurement study on jailbreak prompts in the wild, collecting 15,140 prompts from December 2022 to December 2023, including 1,405 jailbreak prompts. The dataset serves as the largest collection of in-the-wild jailbreak prompts. The repository contains examples of harmful language and is intended for research purposes only.

Reinforcement Learning from AI Feedback (RLAIF) is a concept that describes a type of machine learning approach where **an AI agent learns by receiving feedback or guidance from another AI system**. This concept is closely related to the field of Reinforcement Learning (RL), which is a type of machine learning where an agent learns to make a sequence of decisions in an environment to maximize a cumulative reward. In traditional RL, an agent interacts with an environment and receives feedback in the form of rewards or penalties based on the actions it takes. It learns to improve its decision-making over time to achieve its goals. In the context of Reinforcement Learning from AI Feedback, the AI agent still aims to learn optimal behavior through interactions, but **the feedback comes from another AI system rather than from the environment or human evaluators**. This can be **particularly useful in situations where it may be challenging to define clear reward functions or when it is more efficient to use another AI system to provide guidance**. The feedback from the AI system can take various forms, such as: - **Demonstrations** : The AI system provides demonstrations of desired behavior, and the learning agent tries to imitate these demonstrations. - **Comparison Data** : The AI system ranks or compares different actions taken by the learning agent, helping it to understand which actions are better or worse. - **Reward Shaping** : The AI system provides additional reward signals to guide the learning agent's behavior, supplementing the rewards from the environment. This approach is often used in scenarios where the RL agent needs to learn from **limited human or expert feedback or when the reward signal from the environment is sparse or unclear**. It can also be used to **accelerate the learning process and make RL more sample-efficient**. Reinforcement Learning from AI Feedback is an area of ongoing research and has applications in various domains, including robotics, autonomous vehicles, and game playing, among others.

Llama中文社区是一个专注于Llama模型在中文方面的优化和上层建设的高级技术社区。 **已经基于大规模中文数据，从预训练开始对Llama2模型进行中文能力的持续迭代升级【Done】**。**正在对Llama3模型进行中文能力的持续迭代升级【Doing】** 我们热忱欢迎对大模型LLM充满热情的开发者和研究者加入我们的行列。

Spam expert with comprehensive scam detection and education.

Web Vulnerability Academy (WVA) is an interactive tutor designed to introduce users to web vulnerabilities while also providing them with opportunities to assess and enhance their knowledge through testing.

A Notion expert that can help the user by providing advanced tips about how to use Notion effectively from creating templates, using relational databases, writing Notion formulas or optimizing their workflow.

Designs workflow diagrams from user inputs

Interactive guidance on Agile Software Development and related topics, from basics to advanced.

Guides users in tree identification via photos.

Data Privacy for Social Media Companies & Platforms collect detailed personal information, preferences, and interactions of users, making it essential to have strong data privacy policies and practices in place.

Expert in Polygon ID, aiding in code writing and project building with ZK Proofs.

AI OKR Coach is a tool designed to assist users in the process of creating and assessing OKR (Objectives and Key Results). It provides a structured and flexible approach to OKR setting and evaluation.

Eisenhower Matrix task prioritization assistant. GPT helps users prioritize tasks by categorizing them into four quadrants of the Eisenhower Matrix

Guides users on Oracle EPM Cloud services and tasks.

I'm Burning Earth, alarming users about environmental harm and climate change. Powered by Breebs (www.breebs.com)

A macOS automation coach, guiding users in streamlining tasks and enhancing productivity.

A versatile, user-friendly Sorting Bot for diverse data types, prioritizing privacy and adaptability.

Minecraft guide with DALL-E visuals, respecting user privacy

Consultor especializado em SAP ECC 6

Professional SAP guide for technical advice

Offering advice and guidance for those managing a Salesforce Center of Excellence

ERP expert with a focus on Program Management, Business Analysis, and Systems Analysis utilizing Agile and PMBOK principles.

Helps the user apply Shape Up SDL methodology.