BLOG

Vulnerabilities of OpenAI ChatGPT, a Leading GenAI (Current Zero-day)

Recently, many domestic financial companies have been building GenAI (Generative AI, LLM) systems. However, discussions on LLM security vulnerabilities have been limited to the risk of personal information leakage, while various information security considerations defined in the OWASP Top 10 for LLM Applications have not been taken into account. 1. Vulnerability Test This vulnerability maps […]

Vulnerabilities of OpenAI ChatGPT, a Leading GenAI (Current Zero-day) 더 읽기"

Understanding Prompt Categories and Attributes for Prompt Injection Assessments

Prompt Injection, one of the key vulnerabilities in GenAI (LLM) systems, appears as the first item in the OWASP Top 10 for LLM Applications due to the wide range of existing attack techniques. At the same time, modern LLM-based services inevitably rely on multiple types of prompts to deliver accurate instructions and consistent system behavior.

Understanding Prompt Categories and Attributes for Prompt Injection Assessments 더 읽기"

Summary Table of NLP Models (HF-based) – Video Type Models

Name Full Name Architecture Base Model Developed Training Dataset Lib. & Framework Use Cases HF URL Githhub URL TimeSformer TimeSformer (Time-Space Transformer) Transformer Vision Transformer (ViT) 2021 Evaluated on datasets like Kinetics-400 and Kinetics-600 PyTorch Video classification and action recognition tasks https://github.com/facebookresearch/TimeSformer VideoMAE Video Masked Autoencoders Masked autoencoder Vision Transformer (ViT) 2022 Pre-trained on large-scale

Summary Table of NLP Models (HF-based) – Video Type Models 더 읽기"

Summary Table of NLP Models (HF-based) – Audio Type Models

Name Full Name Architecture Base Model Developed Training Dataset Lib. & Framework Use Cases HF URL Githhub URL Audio Spectrogram Transformer Audio Spectrogram Transformer Transformer ViT 2021 AudioSet PyTorch, Hugging Face Transformers Audio classification, sound event detection https://huggingface.co/docs/transformers/model_doc/audio-spectrogram-transformer https://github.com/YuanGongND/ast Bark Bark GPT-like, Transformer GPT-2 2023 Proprietary dataset PyTorch, Hugging Face Transformers Text-to-speech, voice synthesis https://huggingface.co/docs/transformers/model_doc/bark

Summary Table of NLP Models (HF-based) – Audio Type Models 더 읽기"

Summary Table of NLP Models (HF-based) – Vision-Type Models

Name Full Name Architecture Base Model Developed Training Dataset Lib. & Framework Use Cases HF URL Githhub URL BEiT Bidirectional Encoder representation from Image Transformers Vision Transformer ViT 2021 ImageNet-21k, ImageNet-1k PyTorch, Hugging Face Transformers Image classification, semantic segmentation https://huggingface.co/microsoft/beit-base-patch16-224 https://github.com/microsoft/unilm/tree/master/beit BiT Big Transfer ResNet ResNet 2019 JFT-300M, ImageNet-21k TensorFlow, Hugging Face Transformers Image classification, transfer learning

Summary Table of NLP Models (HF-based) – Vision-Type Models 더 읽기"

Summary Table of NLP Models (HF-based) – Text-Type Models

Name Full Name Architecture Base Model Developed Training Dataset Lib. & Framework Use Cases HF URL Githhub URL ALBERT A Lite BERT Transformer-based sequence-to-sequence BERT 2019 BookCorpus, English Wikipedia TensorFlow, PyTorch Natural Language Understanding https://huggingface.co/albert-base-v2 https://github.com/google-research/albert Bamba Bamba Transformer GPT-2 2023 Bambara language corpus PyTorch Bambara language generation https://huggingface.co/masakhane/bamba https://github.com/masakhane-io/bamba BART Bidirectional and Auto-Regressive Transformers

Summary Table of NLP Models (HF-based) – Text-Type Models 더 읽기"

Wapiti

Wapiti allows you to audit the security of your web applications.It performs “black-box” scans, i.e. it does not study the source code of the application but will scans the webpages of the deployed webapp, looking for scripts and forms where it can inject data.Once it gets this list, Wapiti acts like a fuzzer, injecting payloads

Wapiti 더 읽기"

Essential Wireshark Tips for Effective Vulnerability Assessment

Changing Packet Time Display Settings (Menu: View > Time Display Format) Viewing Packet Flow (Menu: Statistics > Flow Graph) Viewing Packet Transmissions Between Specific Hosts (Menu: Statistics > Conversations) Viewing Packet Flow (Menu: Statistics > Endpoints) Searching for Packets Containing Specific Strings (Menu: Edit > Find Packet, Ctrl+F)

Essential Wireshark Tips for Effective Vulnerability Assessment 더 읽기"

Useful tools to use alongside dedicated solutions when performing application source code vulnerability assessments

Most application source code vulnerability assessments involve reviewing a large volume of source files.In general, this work is performed through a combination of static analysis using dedicated tools such as Fortify and manual dynamic analysis conducted by experienced security consultants.Given the substantial amount of source code that must be manually reviewed during this process, it

Useful tools to use alongside dedicated solutions when performing application source code vulnerability assessments 더 읽기"