Create accountLogin

Recent searches

No recent searches

Search options

Only available when logged in.
101010.pl is one of the many independent Mastodon servers you can use to participate in the fediverse.
101010.pl czyli najstarszy polski serwer Mastodon. Posiadamy wpisy do 2048 znaków.

Administered by:

Server stats:

509
active users

101010.pl: AboutStatusProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.4.0-alpha.5

#aitesting

0 posts0 participants0 posts today
Continued thread
Public
Giskard

◆ Hallucination and factual accuracy
◆ Bias and fairness
◆ Resistance to adversarial attacks
◆ Harmful content prevention

The LLM Benchmark incorporates diverse linguistic and cultural contexts to ensure comprehensiveness, and representative samples will be open-source.

Read about our methodology, and early findings: gisk.ar/3CRFdeB

We will be sharing more results in the coming months 👀

gisk.arGiskard announces a new LLM Evaluation Benchmark during the Paris AI SummitGiskard partners with Google DeepMind to launch an independent multilingual LLM benchmark, evaluating hallucinations and AI security risks.
#AISecurity#AITesting#LLMs
Public
Giskard

🤝 Joined the AI Verify Foundation to strengthen our commitment to responsible AI testing 💚

The AI Verify Foundation, backed by Singapore's IMDA, brings together the global open-source community to develop AI testing frameworks and promote industry standards. Their work is crucial as organizations worldwide seek concrete ways to implement responsible AI practices.
[1/2] 👇

#ResponsibleAI#AITesting#AIGovernance
Continued thread
Public
Giskard

📝 How to participate
1. Join our Discord community: gisk.ar/3V7Wk1q
2. Fill out our quick entry form: gisk.ar/49pcVnH

⏰ Key dates
• Form opens: November 26, 2024
• Entries close: December 10, 2024
• Winners announced: December 11, 2024

Join our Discord and participate in the giveaway to be part of our growing community! ✨

DiscordJoin the Giskard Discord Server!Check out the Giskard community on Discord – hang out with 1023 other members and enjoy free voice and text chat.
#AISecurity#AITesting#discord
Public
Giskard

🌟 Proud of helping thousands of data scientists and ML engineers with #AITesting over the last months 🤯

Building in the open has been our best decision. The transparency of open-source has enabled our library to offer better testing capabilities, helping users ensure more reliable and responsible AI models

This is a milestone we couldn't have imagined when we started Giskard in late 2021 🐢 Thank you to our community for your support over the years 🫶

#AISecurity#OpenSource
Replied in thread
Public
Giskard

📄 Read the full paper: gisk.ar/48tOfcX

#AITesting #AISecurity #LLMs #opensource
[3/3]

arXiv.orgInsights and Current Gaps in Open-Source LLM Vulnerability Scanners: A Comparative AnalysisThis report presents a comparative analysis of open-source vulnerability scanners for conversational large language models (LLMs). As LLMs become integral to various applications, they also present potential attack surfaces, exposed to security risks such as information leakage and jailbreak attacks. Our study evaluates prominent scanners - Garak, Giskard, PyRIT, and CyberSecEval - that adapt red-teaming practices to expose these vulnerabilities. We detail the distinctive features and practical use of these scanners, outline unifying principles of their design and perform quantitative evaluations to compare them. These evaluations uncover significant reliability issues in detecting successful attacks, highlighting a fundamental gap for future development. Additionally, we contribute a preliminary labelled dataset, which serves as an initial step to bridge this gap. Based on the above, we provide strategic recommendations to assist organizations choose the most suitable scanner for their red-teaming needs, accounting for customizability, test suite comprehensiveness, and industry-specific use cases.
ExploreLive feeds
About